This is page 53 of 59. Use http://codebase.md/czlonkowski/n8n-mcp?lines=true&page={x} to view the full context.
# Directory Structure
```
├── _config.yml
├── .claude
│ └── agents
│ ├── code-reviewer.md
│ ├── context-manager.md
│ ├── debugger.md
│ ├── deployment-engineer.md
│ ├── mcp-backend-engineer.md
│ ├── n8n-mcp-tester.md
│ ├── technical-researcher.md
│ └── test-automator.md
├── .dockerignore
├── .env.docker
├── .env.example
├── .env.n8n.example
├── .env.test
├── .env.test.example
├── .github
│ ├── ABOUT.md
│ ├── BENCHMARK_THRESHOLDS.md
│ ├── FUNDING.yml
│ ├── gh-pages.yml
│ ├── secret_scanning.yml
│ └── workflows
│ ├── benchmark-pr.yml
│ ├── benchmark.yml
│ ├── docker-build-fast.yml
│ ├── docker-build-n8n.yml
│ ├── docker-build.yml
│ ├── release.yml
│ ├── test.yml
│ └── update-n8n-deps.yml
├── .gitignore
├── .npmignore
├── ATTRIBUTION.md
├── CHANGELOG.md
├── CLAUDE.md
├── codecov.yml
├── coverage.json
├── data
│ ├── .gitkeep
│ ├── nodes.db
│ ├── nodes.db-shm
│ ├── nodes.db-wal
│ └── templates.db
├── deploy
│ └── quick-deploy-n8n.sh
├── docker
│ ├── docker-entrypoint.sh
│ ├── n8n-mcp
│ ├── parse-config.js
│ └── README.md
├── docker-compose.buildkit.yml
├── docker-compose.extract.yml
├── docker-compose.n8n.yml
├── docker-compose.override.yml.example
├── docker-compose.test-n8n.yml
├── docker-compose.yml
├── Dockerfile
├── Dockerfile.railway
├── Dockerfile.test
├── docs
│ ├── AUTOMATED_RELEASES.md
│ ├── BENCHMARKS.md
│ ├── CHANGELOG.md
│ ├── CLAUDE_CODE_SETUP.md
│ ├── CLAUDE_INTERVIEW.md
│ ├── CODECOV_SETUP.md
│ ├── CODEX_SETUP.md
│ ├── CURSOR_SETUP.md
│ ├── DEPENDENCY_UPDATES.md
│ ├── DOCKER_README.md
│ ├── DOCKER_TROUBLESHOOTING.md
│ ├── FINAL_AI_VALIDATION_SPEC.md
│ ├── FLEXIBLE_INSTANCE_CONFIGURATION.md
│ ├── HTTP_DEPLOYMENT.md
│ ├── img
│ │ ├── cc_command.png
│ │ ├── cc_connected.png
│ │ ├── codex_connected.png
│ │ ├── cursor_tut.png
│ │ ├── Railway_api.png
│ │ ├── Railway_server_address.png
│ │ ├── vsc_ghcp_chat_agent_mode.png
│ │ ├── vsc_ghcp_chat_instruction_files.png
│ │ ├── vsc_ghcp_chat_thinking_tool.png
│ │ └── windsurf_tut.png
│ ├── INSTALLATION.md
│ ├── LIBRARY_USAGE.md
│ ├── local
│ │ ├── DEEP_DIVE_ANALYSIS_2025-10-02.md
│ │ ├── DEEP_DIVE_ANALYSIS_README.md
│ │ ├── Deep_dive_p1_p2.md
│ │ ├── integration-testing-plan.md
│ │ ├── integration-tests-phase1-summary.md
│ │ ├── N8N_AI_WORKFLOW_BUILDER_ANALYSIS.md
│ │ ├── P0_IMPLEMENTATION_PLAN.md
│ │ └── TEMPLATE_MINING_ANALYSIS.md
│ ├── MCP_ESSENTIALS_README.md
│ ├── MCP_QUICK_START_GUIDE.md
│ ├── N8N_DEPLOYMENT.md
│ ├── RAILWAY_DEPLOYMENT.md
│ ├── README_CLAUDE_SETUP.md
│ ├── README.md
│ ├── tools-documentation-usage.md
│ ├── VS_CODE_PROJECT_SETUP.md
│ ├── WINDSURF_SETUP.md
│ └── workflow-diff-examples.md
├── examples
│ └── enhanced-documentation-demo.js
├── fetch_log.txt
├── LICENSE
├── MEMORY_N8N_UPDATE.md
├── MEMORY_TEMPLATE_UPDATE.md
├── monitor_fetch.sh
├── N8N_HTTP_STREAMABLE_SETUP.md
├── n8n-nodes.db
├── P0-R3-TEST-PLAN.md
├── package-lock.json
├── package.json
├── package.runtime.json
├── PRIVACY.md
├── railway.json
├── README.md
├── renovate.json
├── scripts
│ ├── analyze-optimization.sh
│ ├── audit-schema-coverage.ts
│ ├── build-optimized.sh
│ ├── compare-benchmarks.js
│ ├── demo-optimization.sh
│ ├── deploy-http.sh
│ ├── deploy-to-vm.sh
│ ├── export-webhook-workflows.ts
│ ├── extract-changelog.js
│ ├── extract-from-docker.js
│ ├── extract-nodes-docker.sh
│ ├── extract-nodes-simple.sh
│ ├── format-benchmark-results.js
│ ├── generate-benchmark-stub.js
│ ├── generate-detailed-reports.js
│ ├── generate-test-summary.js
│ ├── http-bridge.js
│ ├── mcp-http-client.js
│ ├── migrate-nodes-fts.ts
│ ├── migrate-tool-docs.ts
│ ├── n8n-docs-mcp.service
│ ├── nginx-n8n-mcp.conf
│ ├── prebuild-fts5.ts
│ ├── prepare-release.js
│ ├── publish-npm-quick.sh
│ ├── publish-npm.sh
│ ├── quick-test.ts
│ ├── run-benchmarks-ci.js
│ ├── sync-runtime-version.js
│ ├── test-ai-validation-debug.ts
│ ├── test-code-node-enhancements.ts
│ ├── test-code-node-fixes.ts
│ ├── test-docker-config.sh
│ ├── test-docker-fingerprint.ts
│ ├── test-docker-optimization.sh
│ ├── test-docker.sh
│ ├── test-empty-connection-validation.ts
│ ├── test-error-message-tracking.ts
│ ├── test-error-output-validation.ts
│ ├── test-error-validation.js
│ ├── test-essentials.ts
│ ├── test-expression-code-validation.ts
│ ├── test-expression-format-validation.js
│ ├── test-fts5-search.ts
│ ├── test-fuzzy-fix.ts
│ ├── test-fuzzy-simple.ts
│ ├── test-helpers-validation.ts
│ ├── test-http-search.ts
│ ├── test-http.sh
│ ├── test-jmespath-validation.ts
│ ├── test-multi-tenant-simple.ts
│ ├── test-multi-tenant.ts
│ ├── test-n8n-integration.sh
│ ├── test-node-info.js
│ ├── test-node-type-validation.ts
│ ├── test-nodes-base-prefix.ts
│ ├── test-operation-validation.ts
│ ├── test-optimized-docker.sh
│ ├── test-release-automation.js
│ ├── test-search-improvements.ts
│ ├── test-security.ts
│ ├── test-single-session.sh
│ ├── test-sqljs-triggers.ts
│ ├── test-telemetry-debug.ts
│ ├── test-telemetry-direct.ts
│ ├── test-telemetry-env.ts
│ ├── test-telemetry-integration.ts
│ ├── test-telemetry-no-select.ts
│ ├── test-telemetry-security.ts
│ ├── test-telemetry-simple.ts
│ ├── test-typeversion-validation.ts
│ ├── test-url-configuration.ts
│ ├── test-user-id-persistence.ts
│ ├── test-webhook-validation.ts
│ ├── test-workflow-insert.ts
│ ├── test-workflow-sanitizer.ts
│ ├── test-workflow-tracking-debug.ts
│ ├── update-and-publish-prep.sh
│ ├── update-n8n-deps.js
│ ├── update-readme-version.js
│ ├── vitest-benchmark-json-reporter.js
│ └── vitest-benchmark-reporter.ts
├── SECURITY.md
├── src
│ ├── config
│ │ └── n8n-api.ts
│ ├── data
│ │ └── canonical-ai-tool-examples.json
│ ├── database
│ │ ├── database-adapter.ts
│ │ ├── migrations
│ │ │ └── add-template-node-configs.sql
│ │ ├── node-repository.ts
│ │ ├── nodes.db
│ │ ├── schema-optimized.sql
│ │ └── schema.sql
│ ├── errors
│ │ └── validation-service-error.ts
│ ├── http-server-single-session.ts
│ ├── http-server.ts
│ ├── index.ts
│ ├── loaders
│ │ └── node-loader.ts
│ ├── mappers
│ │ └── docs-mapper.ts
│ ├── mcp
│ │ ├── handlers-n8n-manager.ts
│ │ ├── handlers-workflow-diff.ts
│ │ ├── index.ts
│ │ ├── server.ts
│ │ ├── stdio-wrapper.ts
│ │ ├── tool-docs
│ │ │ ├── configuration
│ │ │ │ ├── get-node-as-tool-info.ts
│ │ │ │ ├── get-node-documentation.ts
│ │ │ │ ├── get-node-essentials.ts
│ │ │ │ ├── get-node-info.ts
│ │ │ │ ├── get-property-dependencies.ts
│ │ │ │ ├── index.ts
│ │ │ │ └── search-node-properties.ts
│ │ │ ├── discovery
│ │ │ │ ├── get-database-statistics.ts
│ │ │ │ ├── index.ts
│ │ │ │ ├── list-ai-tools.ts
│ │ │ │ ├── list-nodes.ts
│ │ │ │ └── search-nodes.ts
│ │ │ ├── guides
│ │ │ │ ├── ai-agents-guide.ts
│ │ │ │ └── index.ts
│ │ │ ├── index.ts
│ │ │ ├── system
│ │ │ │ ├── index.ts
│ │ │ │ ├── n8n-diagnostic.ts
│ │ │ │ ├── n8n-health-check.ts
│ │ │ │ ├── n8n-list-available-tools.ts
│ │ │ │ └── tools-documentation.ts
│ │ │ ├── templates
│ │ │ │ ├── get-template.ts
│ │ │ │ ├── get-templates-for-task.ts
│ │ │ │ ├── index.ts
│ │ │ │ ├── list-node-templates.ts
│ │ │ │ ├── list-tasks.ts
│ │ │ │ ├── search-templates-by-metadata.ts
│ │ │ │ └── search-templates.ts
│ │ │ ├── types.ts
│ │ │ ├── validation
│ │ │ │ ├── index.ts
│ │ │ │ ├── validate-node-minimal.ts
│ │ │ │ ├── validate-node-operation.ts
│ │ │ │ ├── validate-workflow-connections.ts
│ │ │ │ ├── validate-workflow-expressions.ts
│ │ │ │ └── validate-workflow.ts
│ │ │ └── workflow_management
│ │ │ ├── index.ts
│ │ │ ├── n8n-autofix-workflow.ts
│ │ │ ├── n8n-create-workflow.ts
│ │ │ ├── n8n-delete-execution.ts
│ │ │ ├── n8n-delete-workflow.ts
│ │ │ ├── n8n-get-execution.ts
│ │ │ ├── n8n-get-workflow-details.ts
│ │ │ ├── n8n-get-workflow-minimal.ts
│ │ │ ├── n8n-get-workflow-structure.ts
│ │ │ ├── n8n-get-workflow.ts
│ │ │ ├── n8n-list-executions.ts
│ │ │ ├── n8n-list-workflows.ts
│ │ │ ├── n8n-trigger-webhook-workflow.ts
│ │ │ ├── n8n-update-full-workflow.ts
│ │ │ ├── n8n-update-partial-workflow.ts
│ │ │ └── n8n-validate-workflow.ts
│ │ ├── tools-documentation.ts
│ │ ├── tools-n8n-friendly.ts
│ │ ├── tools-n8n-manager.ts
│ │ ├── tools.ts
│ │ └── workflow-examples.ts
│ ├── mcp-engine.ts
│ ├── mcp-tools-engine.ts
│ ├── n8n
│ │ ├── MCPApi.credentials.ts
│ │ └── MCPNode.node.ts
│ ├── parsers
│ │ ├── node-parser.ts
│ │ ├── property-extractor.ts
│ │ └── simple-parser.ts
│ ├── scripts
│ │ ├── debug-http-search.ts
│ │ ├── extract-from-docker.ts
│ │ ├── fetch-templates-robust.ts
│ │ ├── fetch-templates.ts
│ │ ├── rebuild-database.ts
│ │ ├── rebuild-optimized.ts
│ │ ├── rebuild.ts
│ │ ├── sanitize-templates.ts
│ │ ├── seed-canonical-ai-examples.ts
│ │ ├── test-autofix-documentation.ts
│ │ ├── test-autofix-workflow.ts
│ │ ├── test-execution-filtering.ts
│ │ ├── test-node-suggestions.ts
│ │ ├── test-protocol-negotiation.ts
│ │ ├── test-summary.ts
│ │ ├── test-webhook-autofix.ts
│ │ ├── validate.ts
│ │ └── validation-summary.ts
│ ├── services
│ │ ├── ai-node-validator.ts
│ │ ├── ai-tool-validators.ts
│ │ ├── confidence-scorer.ts
│ │ ├── config-validator.ts
│ │ ├── enhanced-config-validator.ts
│ │ ├── example-generator.ts
│ │ ├── execution-processor.ts
│ │ ├── expression-format-validator.ts
│ │ ├── expression-validator.ts
│ │ ├── n8n-api-client.ts
│ │ ├── n8n-validation.ts
│ │ ├── node-documentation-service.ts
│ │ ├── node-similarity-service.ts
│ │ ├── node-specific-validators.ts
│ │ ├── operation-similarity-service.ts
│ │ ├── property-dependencies.ts
│ │ ├── property-filter.ts
│ │ ├── resource-similarity-service.ts
│ │ ├── sqlite-storage-service.ts
│ │ ├── task-templates.ts
│ │ ├── universal-expression-validator.ts
│ │ ├── workflow-auto-fixer.ts
│ │ ├── workflow-diff-engine.ts
│ │ └── workflow-validator.ts
│ ├── telemetry
│ │ ├── batch-processor.ts
│ │ ├── config-manager.ts
│ │ ├── early-error-logger.ts
│ │ ├── error-sanitization-utils.ts
│ │ ├── error-sanitizer.ts
│ │ ├── event-tracker.ts
│ │ ├── event-validator.ts
│ │ ├── index.ts
│ │ ├── performance-monitor.ts
│ │ ├── rate-limiter.ts
│ │ ├── startup-checkpoints.ts
│ │ ├── telemetry-error.ts
│ │ ├── telemetry-manager.ts
│ │ ├── telemetry-types.ts
│ │ └── workflow-sanitizer.ts
│ ├── templates
│ │ ├── batch-processor.ts
│ │ ├── metadata-generator.ts
│ │ ├── README.md
│ │ ├── template-fetcher.ts
│ │ ├── template-repository.ts
│ │ └── template-service.ts
│ ├── types
│ │ ├── index.ts
│ │ ├── instance-context.ts
│ │ ├── n8n-api.ts
│ │ ├── node-types.ts
│ │ └── workflow-diff.ts
│ └── utils
│ ├── auth.ts
│ ├── bridge.ts
│ ├── cache-utils.ts
│ ├── console-manager.ts
│ ├── documentation-fetcher.ts
│ ├── enhanced-documentation-fetcher.ts
│ ├── error-handler.ts
│ ├── example-generator.ts
│ ├── fixed-collection-validator.ts
│ ├── logger.ts
│ ├── mcp-client.ts
│ ├── n8n-errors.ts
│ ├── node-source-extractor.ts
│ ├── node-type-normalizer.ts
│ ├── node-type-utils.ts
│ ├── node-utils.ts
│ ├── npm-version-checker.ts
│ ├── protocol-version.ts
│ ├── simple-cache.ts
│ ├── ssrf-protection.ts
│ ├── template-node-resolver.ts
│ ├── template-sanitizer.ts
│ ├── url-detector.ts
│ ├── validation-schemas.ts
│ └── version.ts
├── test-output.txt
├── test-reinit-fix.sh
├── tests
│ ├── __snapshots__
│ │ └── .gitkeep
│ ├── auth.test.ts
│ ├── benchmarks
│ │ ├── database-queries.bench.ts
│ │ ├── index.ts
│ │ ├── mcp-tools.bench.ts
│ │ ├── mcp-tools.bench.ts.disabled
│ │ ├── mcp-tools.bench.ts.skip
│ │ ├── node-loading.bench.ts.disabled
│ │ ├── README.md
│ │ ├── search-operations.bench.ts.disabled
│ │ └── validation-performance.bench.ts.disabled
│ ├── bridge.test.ts
│ ├── comprehensive-extraction-test.js
│ ├── data
│ │ └── .gitkeep
│ ├── debug-slack-doc.js
│ ├── demo-enhanced-documentation.js
│ ├── docker-tests-README.md
│ ├── error-handler.test.ts
│ ├── examples
│ │ └── using-database-utils.test.ts
│ ├── extracted-nodes-db
│ │ ├── database-import.json
│ │ ├── extraction-report.json
│ │ ├── insert-nodes.sql
│ │ ├── n8n-nodes-base__Airtable.json
│ │ ├── n8n-nodes-base__Discord.json
│ │ ├── n8n-nodes-base__Function.json
│ │ ├── n8n-nodes-base__HttpRequest.json
│ │ ├── n8n-nodes-base__If.json
│ │ ├── n8n-nodes-base__Slack.json
│ │ ├── n8n-nodes-base__SplitInBatches.json
│ │ └── n8n-nodes-base__Webhook.json
│ ├── factories
│ │ ├── node-factory.ts
│ │ └── property-definition-factory.ts
│ ├── fixtures
│ │ ├── .gitkeep
│ │ ├── database
│ │ │ └── test-nodes.json
│ │ ├── factories
│ │ │ ├── node.factory.ts
│ │ │ └── parser-node.factory.ts
│ │ └── template-configs.ts
│ ├── helpers
│ │ └── env-helpers.ts
│ ├── http-server-auth.test.ts
│ ├── integration
│ │ ├── ai-validation
│ │ │ ├── ai-agent-validation.test.ts
│ │ │ ├── ai-tool-validation.test.ts
│ │ │ ├── chat-trigger-validation.test.ts
│ │ │ ├── e2e-validation.test.ts
│ │ │ ├── helpers.ts
│ │ │ ├── llm-chain-validation.test.ts
│ │ │ ├── README.md
│ │ │ └── TEST_REPORT.md
│ │ ├── ci
│ │ │ └── database-population.test.ts
│ │ ├── database
│ │ │ ├── connection-management.test.ts
│ │ │ ├── empty-database.test.ts
│ │ │ ├── fts5-search.test.ts
│ │ │ ├── node-fts5-search.test.ts
│ │ │ ├── node-repository.test.ts
│ │ │ ├── performance.test.ts
│ │ │ ├── template-node-configs.test.ts
│ │ │ ├── template-repository.test.ts
│ │ │ ├── test-utils.ts
│ │ │ └── transactions.test.ts
│ │ ├── database-integration.test.ts
│ │ ├── docker
│ │ │ ├── docker-config.test.ts
│ │ │ ├── docker-entrypoint.test.ts
│ │ │ └── test-helpers.ts
│ │ ├── flexible-instance-config.test.ts
│ │ ├── mcp
│ │ │ └── template-examples-e2e.test.ts
│ │ ├── mcp-protocol
│ │ │ ├── basic-connection.test.ts
│ │ │ ├── error-handling.test.ts
│ │ │ ├── performance.test.ts
│ │ │ ├── protocol-compliance.test.ts
│ │ │ ├── README.md
│ │ │ ├── session-management.test.ts
│ │ │ ├── test-helpers.ts
│ │ │ ├── tool-invocation.test.ts
│ │ │ └── workflow-error-validation.test.ts
│ │ ├── msw-setup.test.ts
│ │ ├── n8n-api
│ │ │ ├── executions
│ │ │ │ ├── delete-execution.test.ts
│ │ │ │ ├── get-execution.test.ts
│ │ │ │ ├── list-executions.test.ts
│ │ │ │ └── trigger-webhook.test.ts
│ │ │ ├── scripts
│ │ │ │ └── cleanup-orphans.ts
│ │ │ ├── system
│ │ │ │ ├── diagnostic.test.ts
│ │ │ │ ├── health-check.test.ts
│ │ │ │ └── list-tools.test.ts
│ │ │ ├── test-connection.ts
│ │ │ ├── types
│ │ │ │ └── mcp-responses.ts
│ │ │ ├── utils
│ │ │ │ ├── cleanup-helpers.ts
│ │ │ │ ├── credentials.ts
│ │ │ │ ├── factories.ts
│ │ │ │ ├── fixtures.ts
│ │ │ │ ├── mcp-context.ts
│ │ │ │ ├── n8n-client.ts
│ │ │ │ ├── node-repository.ts
│ │ │ │ ├── response-types.ts
│ │ │ │ ├── test-context.ts
│ │ │ │ └── webhook-workflows.ts
│ │ │ └── workflows
│ │ │ ├── autofix-workflow.test.ts
│ │ │ ├── create-workflow.test.ts
│ │ │ ├── delete-workflow.test.ts
│ │ │ ├── get-workflow-details.test.ts
│ │ │ ├── get-workflow-minimal.test.ts
│ │ │ ├── get-workflow-structure.test.ts
│ │ │ ├── get-workflow.test.ts
│ │ │ ├── list-workflows.test.ts
│ │ │ ├── smart-parameters.test.ts
│ │ │ ├── update-partial-workflow.test.ts
│ │ │ ├── update-workflow.test.ts
│ │ │ └── validate-workflow.test.ts
│ │ ├── security
│ │ │ ├── command-injection-prevention.test.ts
│ │ │ └── rate-limiting.test.ts
│ │ ├── setup
│ │ │ ├── integration-setup.ts
│ │ │ └── msw-test-server.ts
│ │ ├── telemetry
│ │ │ ├── docker-user-id-stability.test.ts
│ │ │ └── mcp-telemetry.test.ts
│ │ ├── templates
│ │ │ └── metadata-operations.test.ts
│ │ └── workflow-creation-node-type-format.test.ts
│ ├── logger.test.ts
│ ├── MOCKING_STRATEGY.md
│ ├── mocks
│ │ ├── n8n-api
│ │ │ ├── data
│ │ │ │ ├── credentials.ts
│ │ │ │ ├── executions.ts
│ │ │ │ └── workflows.ts
│ │ │ ├── handlers.ts
│ │ │ └── index.ts
│ │ └── README.md
│ ├── node-storage-export.json
│ ├── setup
│ │ ├── global-setup.ts
│ │ ├── msw-setup.ts
│ │ ├── TEST_ENV_DOCUMENTATION.md
│ │ └── test-env.ts
│ ├── test-database-extraction.js
│ ├── test-direct-extraction.js
│ ├── test-enhanced-documentation.js
│ ├── test-enhanced-integration.js
│ ├── test-mcp-extraction.js
│ ├── test-mcp-server-extraction.js
│ ├── test-mcp-tools-integration.js
│ ├── test-node-documentation-service.js
│ ├── test-node-list.js
│ ├── test-package-info.js
│ ├── test-parsing-operations.js
│ ├── test-slack-node-complete.js
│ ├── test-small-rebuild.js
│ ├── test-sqlite-search.js
│ ├── test-storage-system.js
│ ├── unit
│ │ ├── __mocks__
│ │ │ ├── n8n-nodes-base.test.ts
│ │ │ ├── n8n-nodes-base.ts
│ │ │ └── README.md
│ │ ├── database
│ │ │ ├── __mocks__
│ │ │ │ └── better-sqlite3.ts
│ │ │ ├── database-adapter-unit.test.ts
│ │ │ ├── node-repository-core.test.ts
│ │ │ ├── node-repository-operations.test.ts
│ │ │ ├── node-repository-outputs.test.ts
│ │ │ ├── README.md
│ │ │ └── template-repository-core.test.ts
│ │ ├── docker
│ │ │ ├── config-security.test.ts
│ │ │ ├── edge-cases.test.ts
│ │ │ ├── parse-config.test.ts
│ │ │ └── serve-command.test.ts
│ │ ├── errors
│ │ │ └── validation-service-error.test.ts
│ │ ├── examples
│ │ │ └── using-n8n-nodes-base-mock.test.ts
│ │ ├── flexible-instance-security-advanced.test.ts
│ │ ├── flexible-instance-security.test.ts
│ │ ├── http-server
│ │ │ └── multi-tenant-support.test.ts
│ │ ├── http-server-n8n-mode.test.ts
│ │ ├── http-server-n8n-reinit.test.ts
│ │ ├── http-server-session-management.test.ts
│ │ ├── loaders
│ │ │ └── node-loader.test.ts
│ │ ├── mappers
│ │ │ └── docs-mapper.test.ts
│ │ ├── mcp
│ │ │ ├── get-node-essentials-examples.test.ts
│ │ │ ├── handlers-n8n-manager-simple.test.ts
│ │ │ ├── handlers-n8n-manager.test.ts
│ │ │ ├── handlers-workflow-diff.test.ts
│ │ │ ├── lru-cache-behavior.test.ts
│ │ │ ├── multi-tenant-tool-listing.test.ts.disabled
│ │ │ ├── parameter-validation.test.ts
│ │ │ ├── search-nodes-examples.test.ts
│ │ │ ├── tools-documentation.test.ts
│ │ │ └── tools.test.ts
│ │ ├── monitoring
│ │ │ └── cache-metrics.test.ts
│ │ ├── MULTI_TENANT_TEST_COVERAGE.md
│ │ ├── multi-tenant-integration.test.ts
│ │ ├── parsers
│ │ │ ├── node-parser-outputs.test.ts
│ │ │ ├── node-parser.test.ts
│ │ │ ├── property-extractor.test.ts
│ │ │ └── simple-parser.test.ts
│ │ ├── scripts
│ │ │ └── fetch-templates-extraction.test.ts
│ │ ├── services
│ │ │ ├── ai-node-validator.test.ts
│ │ │ ├── ai-tool-validators.test.ts
│ │ │ ├── confidence-scorer.test.ts
│ │ │ ├── config-validator-basic.test.ts
│ │ │ ├── config-validator-edge-cases.test.ts
│ │ │ ├── config-validator-node-specific.test.ts
│ │ │ ├── config-validator-security.test.ts
│ │ │ ├── debug-validator.test.ts
│ │ │ ├── enhanced-config-validator-integration.test.ts
│ │ │ ├── enhanced-config-validator-operations.test.ts
│ │ │ ├── enhanced-config-validator.test.ts
│ │ │ ├── example-generator.test.ts
│ │ │ ├── execution-processor.test.ts
│ │ │ ├── expression-format-validator.test.ts
│ │ │ ├── expression-validator-edge-cases.test.ts
│ │ │ ├── expression-validator.test.ts
│ │ │ ├── fixed-collection-validation.test.ts
│ │ │ ├── loop-output-edge-cases.test.ts
│ │ │ ├── n8n-api-client.test.ts
│ │ │ ├── n8n-validation.test.ts
│ │ │ ├── node-similarity-service.test.ts
│ │ │ ├── node-specific-validators.test.ts
│ │ │ ├── operation-similarity-service-comprehensive.test.ts
│ │ │ ├── operation-similarity-service.test.ts
│ │ │ ├── property-dependencies.test.ts
│ │ │ ├── property-filter-edge-cases.test.ts
│ │ │ ├── property-filter.test.ts
│ │ │ ├── resource-similarity-service-comprehensive.test.ts
│ │ │ ├── resource-similarity-service.test.ts
│ │ │ ├── task-templates.test.ts
│ │ │ ├── template-service.test.ts
│ │ │ ├── universal-expression-validator.test.ts
│ │ │ ├── validation-fixes.test.ts
│ │ │ ├── workflow-auto-fixer.test.ts
│ │ │ ├── workflow-diff-engine.test.ts
│ │ │ ├── workflow-fixed-collection-validation.test.ts
│ │ │ ├── workflow-validator-comprehensive.test.ts
│ │ │ ├── workflow-validator-edge-cases.test.ts
│ │ │ ├── workflow-validator-error-outputs.test.ts
│ │ │ ├── workflow-validator-expression-format.test.ts
│ │ │ ├── workflow-validator-loops-simple.test.ts
│ │ │ ├── workflow-validator-loops.test.ts
│ │ │ ├── workflow-validator-mocks.test.ts
│ │ │ ├── workflow-validator-performance.test.ts
│ │ │ ├── workflow-validator-with-mocks.test.ts
│ │ │ └── workflow-validator.test.ts
│ │ ├── telemetry
│ │ │ ├── batch-processor.test.ts
│ │ │ ├── config-manager.test.ts
│ │ │ ├── event-tracker.test.ts
│ │ │ ├── event-validator.test.ts
│ │ │ ├── rate-limiter.test.ts
│ │ │ ├── telemetry-error.test.ts
│ │ │ ├── telemetry-manager.test.ts
│ │ │ ├── v2.18.3-fixes-verification.test.ts
│ │ │ └── workflow-sanitizer.test.ts
│ │ ├── templates
│ │ │ ├── batch-processor.test.ts
│ │ │ ├── metadata-generator.test.ts
│ │ │ ├── template-repository-metadata.test.ts
│ │ │ └── template-repository-security.test.ts
│ │ ├── test-env-example.test.ts
│ │ ├── test-infrastructure.test.ts
│ │ ├── types
│ │ │ ├── instance-context-coverage.test.ts
│ │ │ └── instance-context-multi-tenant.test.ts
│ │ ├── utils
│ │ │ ├── auth-timing-safe.test.ts
│ │ │ ├── cache-utils.test.ts
│ │ │ ├── console-manager.test.ts
│ │ │ ├── database-utils.test.ts
│ │ │ ├── fixed-collection-validator.test.ts
│ │ │ ├── n8n-errors.test.ts
│ │ │ ├── node-type-normalizer.test.ts
│ │ │ ├── node-type-utils.test.ts
│ │ │ ├── node-utils.test.ts
│ │ │ ├── simple-cache-memory-leak-fix.test.ts
│ │ │ ├── ssrf-protection.test.ts
│ │ │ └── template-node-resolver.test.ts
│ │ └── validation-fixes.test.ts
│ └── utils
│ ├── assertions.ts
│ ├── builders
│ │ └── workflow.builder.ts
│ ├── data-generators.ts
│ ├── database-utils.ts
│ ├── README.md
│ └── test-helpers.ts
├── thumbnail.png
├── tsconfig.build.json
├── tsconfig.json
├── types
│ ├── mcp.d.ts
│ └── test-env.d.ts
├── verify-telemetry-fix.js
├── versioned-nodes.md
├── vitest.config.benchmark.ts
├── vitest.config.integration.ts
└── vitest.config.ts
```
# Files
--------------------------------------------------------------------------------
/docs/CHANGELOG.md:
--------------------------------------------------------------------------------
```markdown
1 | # Changelog
2 |
3 | All notable changes to this project will be documented in this file.
4 |
5 | The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6 | and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7 |
8 | ## [Unreleased] - Phase 0: Connection Operations Critical Fixes
9 |
10 | ### Fixed
11 | - **🐛 CRITICAL: Fixed `addConnection` sourceIndex handling (Issue #272, discovered in hands-on testing)**
12 | - Multi-output nodes (IF, Switch) now work correctly with sourceIndex parameter
13 | - Changed from `||` to `??` operator to properly handle explicit 0 values
14 | - Added defensive array validation before accessing indices
15 | - Improves rating from 3/10 to 8/10 for multi-output node scenarios
16 | - **Impact**: IF nodes, Switch nodes, and all conditional routing now reliable
17 |
18 | - **🐛 CRITICAL: Added runtime validation for `updateConnection` (Issue #272, #204)**
19 | - Prevents server crashes when `updates` object is missing
20 | - Provides helpful error message with:
21 | - Clear explanation of what's wrong
22 | - Correct format example
23 | - Suggestion to use removeConnection + addConnection for rewiring
24 | - Validates `updates` is an object, not string or other type
25 | - **Impact**: No more cryptic "Cannot read properties of undefined" crashes
26 |
27 | ### Enhanced
28 | - **Error Messages**: `updateConnection` errors now include actionable guidance
29 | - Example format shown in error
30 | - Alternative approaches suggested (removeConnection + addConnection)
31 | - Clear explanation that updateConnection modifies properties, not targets
32 |
33 | ### Testing
34 | - Added 8 comprehensive tests for Phase 0 fixes
35 | - 2 tests for updateConnection validation (missing updates, invalid type)
36 | - 5 tests for sourceIndex handling (IF nodes, parallel execution, Switch nodes, explicit 0)
37 | - 1 test for complex multi-output routing scenarios
38 | - All 126 existing tests still passing
39 |
40 | ### Documentation
41 | - Updated tool documentation to clarify:
42 | - `addConnection` now properly handles sourceIndex (Phase 0 fix noted)
43 | - `updateConnection` REQUIRES 'updates' object (Phase 0 validation noted)
44 | - Added pitfalls about updateConnection limitations
45 | - Clarified that updateConnection modifies properties, NOT connection targets
46 |
47 | ### Developer Experience
48 | - More defensive programming throughout connection operations
49 | - Better use of nullish coalescing (??) vs. logical OR (||)
50 | - Clear inline comments explaining expected behavior
51 | - Improved type safety with runtime guards
52 |
53 | ### References
54 | - Comprehensive analysis: `docs/local/connection-operations-deep-dive-and-improvement-plan.md`
55 | - Based on hands-on testing with n8n-mcp-tester agent
56 | - Overall experience rating improved from 4.5/10 to estimated 6/10
57 |
58 | ## [2.14.4] - 2025-09-30
59 |
60 | ### Added
61 | - **Workflow Cleanup Operations**: Two new operations for `n8n_update_partial_workflow` to handle broken workflow recovery
62 | - `cleanStaleConnections`: Automatically removes all connections referencing non-existent nodes
63 | - Essential after node renames or deletions that leave dangling connection references
64 | - Supports `dryRun: true` mode to preview what would be removed
65 | - Removes both source and target stale connections
66 | - `replaceConnections`: Replace entire connections object in a single operation
67 | - Faster than crafting many individual connection operations
68 | - Useful for bulk connection rewiring
69 |
70 | - **Graceful Error Handling for Connection Operations**: Enhanced `removeConnection` operation
71 | - New `ignoreErrors` flag: When `true`, operation succeeds even if connection doesn't exist
72 | - Perfect for cleanup scenarios where you're not sure if connections exist
73 | - Maintains backwards compatibility (defaults to `false` for strict validation)
74 |
75 | - **Best-Effort Mode**: New `continueOnError` mode for `WorkflowDiffRequest`
76 | - Apply valid operations even if some fail
77 | - Returns detailed results with `applied` and `failed` operation indices
78 | - Breaks atomic guarantees intentionally for bulk cleanup scenarios
79 | - Maintains atomic mode as default for safety
80 |
81 | ### Enhanced
82 | - **Tool Documentation**: Updated `n8n_update_partial_workflow` documentation
83 | - Added examples for cleanup scenarios
84 | - Documented new operation types and modes
85 | - Added best practices for workflow recovery
86 | - Clarified atomic vs. best-effort behavior
87 |
88 | - **Type System**: Extended workflow diff types
89 | - Added `CleanStaleConnectionsOperation` interface
90 | - Added `ReplaceConnectionsOperation` interface
91 | - Extended `WorkflowDiffResult` with `applied`, `failed`, and `staleConnectionsRemoved` fields
92 | - Updated type guards for new connection operations
93 |
94 | ### Testing
95 | - Added comprehensive test suite for v2.14.4 features
96 | - 15 new tests covering all new operations and modes
97 | - Tests for cleanStaleConnections with various stale scenarios
98 | - Tests for replaceConnections validation
99 | - Tests for ignoreErrors flag behavior
100 | - Tests for continueOnError mode with mixed success/failure
101 | - Backwards compatibility verification tests
102 |
103 | ### Impact
104 | - **Time Saved**: Reduces broken workflow fix time from 10-15 minutes to 30 seconds
105 | - **Token Efficiency**: `cleanStaleConnections` is 1 operation vs 10+ manual operations
106 | - **User Experience**: Dramatically improved workflow recovery capabilities
107 | - **Backwards Compatibility**: 100% - all additions are optional and default to existing behavior
108 |
109 | ## [2.13.2] - 2025-01-24
110 |
111 | ### Added
112 | - **Operation and Resource Validation with Intelligent Suggestions**: New similarity services for n8n node configuration validation
113 | - `OperationSimilarityService`: Validates operations and suggests similar alternatives using Levenshtein distance and pattern matching
114 | - `ResourceSimilarityService`: Validates resources with automatic plural/singular conversion and typo detection
115 | - Provides "Did you mean...?" suggestions when invalid operations or resources are used
116 | - Example: `operation: "listFiles"` suggests `"search"` for Google Drive nodes
117 | - Example: `resource: "files"` suggests singular `"file"` with 95% confidence
118 | - Confidence-based suggestions (minimum 30% threshold) with contextual fix messages
119 | - Resource-aware operation filtering ensures suggestions are contextually appropriate
120 | - 5-minute cache duration for performance optimization
121 | - Integrated into `EnhancedConfigValidator` for seamless validation flow
122 |
123 | - **Custom Error Handling**: New `ValidationServiceError` class for better error management
124 | - Proper error chaining with cause tracking
125 | - Specialized factory methods for common error scenarios
126 | - Type-safe error propagation throughout the validation pipeline
127 |
128 | ### Enhanced
129 | - **Code Quality and Security Improvements** (based on code review feedback):
130 | - Safe JSON parsing with try-catch error boundaries
131 | - Type guards for safe property access (`getOperationValue`, `getResourceValue`)
132 | - Memory leak prevention with periodic cache cleanup
133 | - Performance optimization with early termination for exact matches
134 | - Replaced magic numbers with named constants for better maintainability
135 | - Comprehensive JSDoc documentation for all public methods
136 | - Improved confidence calculation for typos and transpositions
137 |
138 | ### Fixed
139 | - **Test Compatibility**: Updated test expectations to correctly handle exact match scenarios
140 | - **Cache Management**: Fixed cache cleanup to prevent unbounded memory growth
141 | - **Validation Deduplication**: Enhanced config validator now properly replaces base validator errors with detailed suggestions
142 |
143 | ### Testing
144 | - Added comprehensive test coverage for similarity services (37 new tests)
145 | - All unit tests passing with proper edge case handling
146 | - Integration confirmed via n8n-mcp-tester agent validation
147 |
148 | ## [2.13.1] - 2025-01-24
149 |
150 | ### Changed
151 | - **Removed 5-operation limit from n8n_update_partial_workflow**: The workflow diff engine now supports unlimited operations per request
152 | - Previously limited to 5 operations for "transactional integrity"
153 | - Analysis revealed the limit was unnecessary - the clone-validate-apply pattern already ensures atomicity
154 | - All operations are validated before any are applied, maintaining data integrity
155 | - Enables complex workflow refactoring in single API calls
156 | - Updated documentation and examples to demonstrate large batch operations (26+ operations)
157 |
158 | ## [2.13.0] - 2025-01-24
159 |
160 | ### Added
161 | - **Webhook Path Autofixer**: Automatically generates UUIDs for webhook nodes missing path configuration
162 | - Generates unique UUID for both `path` parameter and `webhookId` field
163 | - Conditionally updates typeVersion to 2.1 only when < 2.1 to ensure compatibility
164 | - High confidence fix (95%) as UUID generation is deterministic
165 | - Resolves webhook nodes showing "?" in the n8n UI
166 |
167 | - **Enhanced Node Type Suggestions**: Intelligent node type correction with similarity matching
168 | - Multi-factor scoring system: name similarity, category match, package match, pattern match
169 | - Handles deprecated package prefixes (n8n-nodes-base. → nodes-base.)
170 | - Corrects capitalization mistakes (HttpRequest → httpRequest)
171 | - Suggests correct packages (nodes-base.openai → nodes-langchain.openAi)
172 | - Only auto-fixes suggestions with ≥90% confidence
173 | - 5-minute cache for performance optimization
174 |
175 | - **n8n_autofix_workflow Tool**: New MCP tool for automatic workflow error correction
176 | - Comprehensive documentation with examples and best practices
177 | - Supports 5 fix types: expression-format, typeversion-correction, error-output-config, node-type-correction, webhook-missing-path
178 | - Confidence-based system (high/medium/low) for safe fixes
179 | - Preview mode to review changes before applying
180 | - Integrated with workflow validation pipeline
181 |
182 | ### Fixed
183 | - **Security**: Eliminated ReDoS vulnerability in NodeSimilarityService
184 | - Replaced all regex patterns with string-based matching
185 | - No performance impact while maintaining accuracy
186 |
187 | - **Performance**: Optimized similarity matching algorithms
188 | - Levenshtein distance algorithm optimized from O(m*n) space to O(n)
189 | - Added early termination for performance improvement
190 | - Cache invalidation with version tracking prevents memory leaks
191 |
192 | - **Code Quality**: Improved maintainability and type safety
193 | - Extracted magic numbers into named constants
194 | - Added proper type guards for runtime safety
195 | - Created centralized node-type-utils for consistent type normalization
196 | - Fixed silent failures in setNestedValue operations
197 |
198 | ### Changed
199 | - Template sanitizer now includes defensive null checks for runtime safety
200 | - Workflow validator uses centralized type normalization utility
201 |
202 | ## [2.12.2] - 2025-01-22
203 |
204 | ### Changed
205 | - Updated n8n dependencies to latest versions:
206 | - n8n: 1.111.0 → 1.112.3
207 | - n8n-core: 1.110.0 → 1.111.0
208 | - n8n-workflow: 1.108.0 → 1.109.0
209 | - @n8n/n8n-nodes-langchain: 1.110.0 → 1.111.1
210 | - Rebuilt node database with 536 nodes (438 from n8n-nodes-base, 98 from langchain)
211 |
212 | ## [2.12.1] - 2025-01-21
213 |
214 | ### Added
215 | - **Comprehensive Expression Format Validation System**: Three-tier validation strategy for n8n expressions
216 | - **Universal Expression Validator**: 100% reliable detection of expression format issues
217 | - Enforces required `=` prefix for all expressions `{{ }}`
218 | - Validates expression syntax (bracket matching, empty expressions)
219 | - Detects common mistakes (template literals, nested brackets, double prefixes)
220 | - Provides confidence score of 1.0 for universal rules
221 | - **Confidence-Based Node-Specific Recommendations**: Intelligent resource locator suggestions
222 | - Confidence scoring system (0.0 to 1.0) for field-specific recommendations
223 | - High confidence (≥0.8): Exact field matches for known nodes (GitHub owner/repository, Slack channels)
224 | - Medium confidence (≥0.5): Field pattern matches (fields ending in Id, Key, Name)
225 | - Factors: exact field match, field patterns, value patterns, node category
226 | - **Resource Locator Format Detection**: Identifies fields needing `__rl` structure
227 | - Validates resource locator mode (id, url, expression, name, list)
228 | - Auto-fixes missing prefixes in resource locator values
229 | - Provides clear JSON examples showing correct format
230 | - **Enhanced Safety Features**:
231 | - Recursion depth protection (MAX_RECURSION_DEPTH = 100) prevents infinite loops
232 | - Pattern matching precision using exact/prefix matching instead of includes()
233 | - Circular reference detection with WeakSet
234 | - **Separation of Concerns**: Clean architecture for maintainability
235 | - Universal rules separated from node-specific intelligence
236 | - Confidence-based application of suggestions
237 | - Future-proof design that works with any n8n node
238 |
239 | ## [2.12.1] - 2025-09-22
240 |
241 | ### Fixed
242 | - **Error Output Validation**: Enhanced workflow validator to detect incorrect error output configurations
243 | - Detects when multiple nodes are incorrectly placed in the same output array (main[0])
244 | - Validates that error handlers are properly connected to main[1] (error output) instead of main[0]
245 | - Cross-validates onError property ('continueErrorOutput') matches actual connection structure
246 | - Provides clear, actionable error messages with JSON examples showing correct configuration
247 | - Uses heuristic detection for error handler nodes (names containing "error", "fail", "catch", etc.)
248 | - Added comprehensive test coverage with 16+ test cases
249 |
250 | ### Improved
251 | - **Validation Messages**: Error messages now include detailed JSON examples showing both incorrect and correct configurations
252 | - **Pattern Detection**: Fixed `checkWorkflowPatterns` to check main[1] for error outputs instead of non-existent outputs.error
253 | - **Test Coverage**: Added new test file `workflow-validator-error-outputs.test.ts` with extensive error output validation scenarios
254 |
255 | ## [2.12.0] - 2025-09-19
256 |
257 | ### Added
258 | - **Flexible Instance Configuration**: Complete multi-instance support for serving multiple n8n instances dynamically
259 | - New `InstanceContext` interface for runtime configuration without multi-tenancy implications
260 | - Dual-mode API client supporting both singleton (env vars) and instance-specific configurations
261 | - LRU cache with SHA-256 hashing for secure client management (100 instances, 30-min TTL)
262 | - Comprehensive input validation preventing injection attacks and invalid configurations
263 | - Session context management in HTTP server for per-session instance configuration
264 | - 100% backward compatibility - existing deployments work unchanged
265 | - Full test coverage with 83 new tests covering security, caching, and validation
266 |
267 | ### Security
268 | - **SHA-256 Cache Key Hashing**: All instance identifiers are hashed before caching
269 | - **Input Validation**: Comprehensive validation for URLs, API keys, and numeric parameters
270 | - **Secure Logging**: Sensitive data never logged, only partial hashes for debugging
271 | - **Memory Management**: LRU eviction and TTL prevent unbounded growth
272 | - **URL Validation**: Blocks dangerous protocols (file://, javascript://, etc.)
273 |
274 | ### Performance
275 | - **Efficient Caching**: LRU cache with automatic cleanup reduces API client creation
276 | - **Fast Lookups**: SHA-256 hashed keys for O(1) cache access
277 | - **Memory Optimized**: Maximum 100 concurrent instances with 30-minute TTL
278 | - **Token Savings**: Reuses existing clients instead of recreating
279 |
280 | ### Documentation
281 | - Added comprehensive [Flexible Instance Configuration Guide](./FLEXIBLE_INSTANCE_CONFIGURATION.md)
282 | - Detailed architecture, usage examples, and security considerations
283 | - Migration guide for existing deployments
284 | - Complete API documentation for InstanceContext
285 |
286 | ## [2.11.3] - 2025-09-17
287 |
288 | ### Fixed
289 | - **n8n_update_partial_workflow Tool**: Fixed critical bug where updateNode and updateConnection operations were using incorrect property name
290 | - Changed from `changes` property to `updates` property to match documentation and expected behavior
291 | - Resolves issue where AI agents would break workflow connections when updating nodes
292 | - Fixes GitHub issues #159 (update_partial_workflow is invalid) and #168 (partial workflow update returns error)
293 | - All related tests updated to use correct property name
294 |
295 | ## [2.11.2] - 2025-09-16
296 |
297 | ### Updated
298 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
299 | - n8n: 1.110.1 → 1.111.0
300 | - n8n-core: 1.109.0 → 1.110.0
301 | - n8n-workflow: 1.107.0 → 1.108.0
302 | - @n8n/n8n-nodes-langchain: 1.109.1 → 1.110.0
303 | - **Node Database**: Rebuilt with 535 nodes from updated n8n packages
304 | - **Templates**: Preserved all 2,598 workflow templates with metadata intact
305 | - All critical nodes validated successfully (httpRequest, code, slack, agent)
306 | - Test suite: 1,911 tests passing, 5 flaky performance tests failing (99.7% pass rate)
307 |
308 | ## [2.11.1] - 2025-09-15
309 |
310 | ### Added
311 | - **Optional Fields Parameter for search_templates**: Enhanced search_templates tool with field filtering capability
312 | - New optional `fields` parameter accepts an array of field names to include in response
313 | - Supported fields: 'id', 'name', 'description', 'author', 'nodes', 'views', 'created', 'url', 'metadata'
314 | - Reduces response size by 70-98% when requesting only specific fields (e.g., just id and name)
315 | - Maintains full backward compatibility - existing calls without fields parameter work unchanged
316 | - Example: `search_templates({query: "slack", fields: ["id", "name"]})` returns minimal data
317 | - Significantly improves AI agent performance by reducing token usage
318 |
319 | ### Added
320 | - **Fuzzy Node Type Matching for Templates**: Improved template discovery with flexible node type resolution
321 | - Templates can now be found using simple node names: `["slack"]` instead of `["n8n-nodes-base.slack"]`
322 | - Accepts various input formats: bare names, partial prefixes, and case variations
323 | - Automatically expands related node types: `["email"]` finds Gmail, email send, and related templates
324 | - `["slack"]` also finds `slackTrigger` templates
325 | - Case-insensitive matching: `["Slack"]`, `["WEBHOOK"]`, `["HttpRequest"]` all work
326 | - Backward compatible - existing exact formats continue working
327 | - Reduces failed queries by approximately 50%
328 | - Added `template-node-resolver.ts` utility for node type resolution
329 | - Added 23 tests for template node resolution
330 | - **Structured Template Metadata System**: Comprehensive metadata for intelligent template discovery
331 | - Generated metadata for 2,534 templates (97.5% coverage) using OpenAI's batch API
332 | - Rich metadata structure: categories, complexity, use cases, setup time, required services, key features, target audience
333 | - New `search_templates_by_metadata` tool for advanced filtering by multiple criteria
334 | - Enhanced `list_templates` tool with optional `includeMetadata` parameter
335 | - Templates now always include descriptions in list responses
336 | - Metadata enables filtering by complexity level (simple/medium/complex)
337 | - Filter by estimated setup time ranges (5-480 minutes)
338 | - Filter by required external services (OpenAI, Slack, Google, etc.)
339 | - Filter by target audience (developers, marketers, analysts, etc.)
340 | - Multiple filter combinations supported for precise template discovery
341 | - SQLite JSON extraction for efficient metadata queries
342 | - Batch processing with OpenAI's gpt-4o-mini model for cost efficiency
343 | - Added comprehensive tool documentation for new metadata features
344 | - New database columns: metadata_json, metadata_generated_at
345 | - Repository methods for metadata search and filtering
346 |
347 | ## [2.11.0] - 2025-01-14
348 |
349 | ### Added
350 | - **Comprehensive Template Pagination**: All template search and list tools now return paginated responses
351 | - Consistent `PaginatedResponse` format with `items`, `total`, `limit`, `offset`, and `hasMore` fields
352 | - Customizable limits (1-100) and offset parameters for all template tools
353 | - Count methods for accurate pagination information across all template queries
354 | - **New `list_templates` Tool**: Efficient browsing of all available templates
355 | - Returns minimal data (id, name, views, nodeCount) for quick overview
356 | - Supports sorting by views, created_at, or name
357 | - Optimized for discovering templates without downloading full workflow data
358 | - **Flexible Template Retrieval Modes**: Enhanced `get_template` with three response modes
359 | - `nodes_only`: Returns just node types and names (minimal tokens)
360 | - `structure`: Returns nodes with positions and connections (moderate detail)
361 | - `full`: Returns complete workflow JSON (default, maximum detail)
362 | - Reduces token usage by 80-90% in minimal modes
363 |
364 | ### Enhanced
365 | - **Template Database Compression**: Implemented gzip compression for workflow JSONs
366 | - Workflow data compressed from ~75MB to 12.10MB (84% reduction)
367 | - Database size reduced from 117MB to 48MB despite 5x more templates
368 | - Transparent compression/decompression with base64 encoding
369 | - No API changes - compression is handled internally
370 | - **Template Quality Filtering**: Automatic filtering of low-quality templates
371 | - Templates with ≤10 views are excluded from the database
372 | - Expanded coverage from 499 to 2,596 high-quality templates (5x increase)
373 | - Filtered 4,505 raw templates down to 2,596 based on popularity
374 | - Ensures AI agents work with proven, valuable workflows
375 | - **Enhanced Database Statistics**: Template metrics now included
376 | - Shows total template count, average/min/max views
377 | - Provides complete database overview including template coverage
378 |
379 | ### Performance
380 | - **Database Optimization**: 59% size reduction while storing 5x more content
381 | - Previous: ~40MB database with 499 templates
382 | - Current: ~48MB database with 2,596 templates
383 | - Without compression would be ~120MB+
384 | - **Token Efficiency**: 80-90% reduction in response size for minimal queries
385 | - `list_templates`: ~10 tokens per template vs 100+ for full data
386 | - `get_template` with `nodes_only`: Returns just essential node information
387 | - Pagination prevents overwhelming responses for large result sets
388 |
389 | ### Fixed
390 | - **Test Suite Compatibility**: Updated all tests for new template system
391 | - Fixed parameter validation tests to expect new method signatures
392 | - Updated integration tests to use templates with >10 views
393 | - Removed redundant test files that were testing at wrong abstraction level
394 | - All 1,700+ tests now passing
395 |
396 | ## [2.10.9] - 2025-01-09
397 |
398 | ### Changed
399 | - **Dependencies**: Updated n8n packages to 1.110.1
400 | - n8n: 1.109.2 → 1.110.1
401 | - n8n-core: 1.108.0 → 1.109.0
402 | - n8n-workflow: 1.106.0 → 1.107.0
403 | - @n8n/n8n-nodes-langchain: 1.108.1 → 1.109.1
404 |
405 | ### Updated
406 | - **Node Database**: Rebuilt with 536 nodes from updated n8n packages
407 | - **Templates**: Refreshed workflow templates database with latest 499 templates from n8n.io
408 |
409 | ## [2.10.8] - 2025-09-04
410 |
411 | ### Updated
412 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
413 | - n8n: 1.107.4 → 1.109.2
414 | - @n8n/n8n-nodes-langchain: 1.106.2 → 1.109.1
415 | - n8n-nodes-base: 1.106.3 → 1.108.0 (via dependencies)
416 | - **Node Database**: Rebuilt with 535 nodes from updated n8n packages
417 | - **Node.js Compatibility**: Optimized for Node.js v22.17.0 LTS
418 | - Enhanced better-sqlite3 native binary compatibility
419 | - Fixed SQL.js fallback mode for environments without native binaries
420 | - **CI/CD Improvements**: Fixed Rollup native module compatibility for GitHub Actions
421 | - Added explicit platform-specific rollup binaries for cross-platform builds
422 | - Resolved npm ci failures in Linux CI environment
423 | - Fixed package-lock.json synchronization issues
424 | - **Platform Support**: Enhanced cross-platform deployment compatibility
425 | - macOS ARM64 and Linux x64 platform binaries included
426 | - Improved npm package distribution with proper dependency resolution
427 | - All 1,728+ tests passing with updated dependencies
428 |
429 | ### Fixed
430 | - **CI/CD Pipeline**: Resolved test failures in GitHub Actions
431 | - Fixed pyodide version conflicts between langchain dependencies
432 | - Regenerated package-lock.json with proper dependency resolution
433 | - Fixed Rollup native module loading in Linux CI environment
434 | - **Database Compatibility**: Enhanced SQL.js fallback reliability
435 | - Improved parameter binding and state management
436 | - Fixed statement cleanup to prevent memory leaks
437 | - **Deployment Reliability**: Better handling of platform-specific dependencies
438 | - npm ci now works consistently across development and CI environments
439 |
440 | ## [2.10.5] - 2025-08-20
441 |
442 | ### Updated
443 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
444 | - n8n: 1.106.3 → 1.107.4
445 | - n8n-core: 1.105.3 → 1.106.2
446 | - n8n-workflow: 1.103.3 → 1.104.1
447 | - @n8n/n8n-nodes-langchain: 1.105.3 → 1.106.2
448 | - **Node Database**: Rebuilt with 535 nodes from updated n8n packages
449 | - All tests passing with updated dependencies
450 |
451 | ## [2.10.4] - 2025-08-12
452 |
453 | ### Updated
454 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
455 | - n8n: 1.105.2 → 1.106.3
456 | - n8n-core: 1.104.1 → 1.105.3
457 | - n8n-workflow: 1.102.1 → 1.103.3
458 | - @n8n/n8n-nodes-langchain: 1.104.1 → 1.105.3
459 | - **Node Database**: Rebuilt with 535 nodes from updated n8n packages
460 | - All 1,728 tests passing with updated dependencies
461 |
462 | ## [2.10.3] - 2025-08-07
463 |
464 | ### Fixed
465 | - **Validation System Robustness**: Fixed multiple critical validation issues affecting AI agents and workflow validation (fixes #58, #68, #70, #73)
466 | - **Issue #73**: Fixed `validate_node_minimal` crash when config is undefined
467 | - Added safe property access with optional chaining (`config?.resource`)
468 | - Tool now handles undefined, null, and malformed configs gracefully
469 | - **Issue #58**: Fixed `validate_node_operation` crash on invalid nodeType
470 | - Added type checking before calling string methods
471 | - Prevents "Cannot read properties of undefined (reading 'replace')" error
472 | - **Issue #70**: Fixed validation profile settings being ignored
473 | - Extended profile parameter to all validation phases (nodes, connections, expressions)
474 | - Added Sticky Notes filtering to reduce false positives
475 | - Enhanced cycle detection to allow legitimate loops (SplitInBatches)
476 | - **Issue #68**: Added error recovery suggestions for AI agents
477 | - New `addErrorRecoverySuggestions()` method provides actionable recovery steps
478 | - Categorizes errors and suggests specific fixes for each type
479 | - Helps AI agents self-correct when validation fails
480 |
481 | ### Added
482 | - **Input Validation System**: Comprehensive validation for all MCP tool inputs
483 | - Created `validation-schemas.ts` with custom validation utilities
484 | - No external dependencies - pure TypeScript implementation
485 | - Tool-specific validation schemas for all MCP tools
486 | - Clear error messages with field-level details
487 | - **Enhanced Cycle Detection**: Improved detection of legitimate loops vs actual cycles
488 | - Recognizes SplitInBatches loop patterns as valid
489 | - Reduces false positive cycle warnings
490 | - **Comprehensive Test Suite**: Added 16 tests covering all validation fixes
491 | - Tests for crash prevention with malformed inputs
492 | - Tests for profile behavior across validation phases
493 | - Tests for error recovery suggestions
494 | - Tests for legitimate loop patterns
495 |
496 | ### Enhanced
497 | - **Validation Profiles**: Now consistently applied across all validation phases
498 | - `minimal`: Reduces warnings for basic validation
499 | - `runtime`: Standard validation for production workflows
500 | - `ai-friendly`: Optimized for AI agent workflow creation
501 | - `strict`: Maximum validation for critical workflows
502 | - **Error Messages**: More helpful and actionable for both humans and AI agents
503 | - Specific recovery suggestions for common errors
504 | - Clear guidance on fixing validation issues
505 | - Examples of correct configurations
506 |
507 | ## [2.10.2] - 2025-08-05
508 |
509 | ### Updated
510 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
511 | - n8n: 1.104.1 → 1.105.2
512 | - n8n-core: 1.103.1 → 1.104.1
513 | - n8n-workflow: 1.101.0 → 1.102.1
514 | - @n8n/n8n-nodes-langchain: 1.103.1 → 1.104.1
515 | - **Node Database**: Rebuilt with 534 nodes from updated n8n packages
516 | - **Template Library**: Fetched 499 workflow templates from the last 12 months
517 | - Templates are filtered to include only those created or updated within the past year
518 | - This ensures the template library contains fresh and actively maintained workflows
519 | - All 1,620 tests passing with updated dependencies
520 |
521 | ## [2.10.1] - 2025-08-02
522 |
523 | ### Fixed
524 | - **Memory Leak in SimpleCache**: Fixed critical memory leak causing MCP server connection loss after several hours (fixes #118)
525 | - Added proper timer cleanup in `SimpleCache.destroy()` method
526 | - Updated MCP server shutdown to clean up cache timers
527 | - Enhanced HTTP server error handling with transport error handlers
528 | - Fixed event listener cleanup to prevent accumulation
529 | - Added comprehensive test coverage for memory leak prevention
530 |
531 | ## [2.10.0] - 2025-08-02
532 |
533 | ### Added
534 | - **Automated Release System**: Complete CI/CD pipeline for automated releases on version bump
535 | - GitHub Actions workflow (`.github/workflows/release.yml`) with 7 coordinated jobs
536 | - Automatic version detection and changelog extraction
537 | - Multi-artifact publishing: GitHub releases, NPM package, Docker images
538 | - Interactive release preparation tool (`npm run prepare:release`)
539 | - Comprehensive release testing tool (`npm run test:release-automation`)
540 | - Full documentation in `docs/AUTOMATED_RELEASES.md`
541 | - Zero-touch releases: version bump → automatic everything
542 |
543 | ### Security
544 | - **CI/CD Security Enhancements**:
545 | - Replaced deprecated `actions/create-release@v1` with secure `gh` CLI
546 | - Fixed git checkout vulnerability using safe `git show` commands
547 | - Fixed command injection risk using proper argument arrays
548 | - Added concurrency control to prevent simultaneous releases
549 | - Added disk space checks before resource-intensive operations
550 | - Implemented confirmation gates for destructive operations
551 |
552 | ### Changed
553 | - **Dockerfile Consolidation**: Removed redundant `Dockerfile.n8n` in favor of single optimized `Dockerfile`
554 | - n8n packages are not required at runtime for N8N_MODE functionality
555 | - Standard image works perfectly with `N8N_MODE=true` environment variable
556 | - Reduces build complexity and maintenance overhead
557 | - Image size reduced by 500MB+ (no unnecessary n8n packages)
558 | - Build time improved from 8+ minutes to 1-2 minutes
559 |
560 | ### Added (CI/CD Features)
561 | - **Developer Tools**:
562 | - `scripts/prepare-release.js`: Interactive guided release tool
563 | - `scripts/test-release-automation.js`: Validates entire release setup
564 | - `scripts/extract-changelog.js`: Modular changelog extraction
565 | - **Release Automation Features**:
566 | - NPM publishing with 3-retry mechanism for network resilience
567 | - Multi-platform Docker builds (amd64, arm64)
568 | - Semantic version validation and prerelease detection
569 | - Automatic documentation badge updates
570 | - Runtime-optimized NPM package (8 deps vs 50+, ~50MB vs 1GB+)
571 |
572 | ### Fixed
573 | - Fixed missing `axios` dependency in `package.runtime.json` causing Docker build failures
574 |
575 | ## [2.9.1] - 2025-08-02
576 |
577 | ### Fixed
578 | - **Fixed Collection Validation**: Fixed critical issue where AI agents created invalid fixedCollection structures causing "propertyValues[itemName] is not iterable" error (fixes #90)
579 | - Created generic `FixedCollectionValidator` utility class that handles 12 different node types
580 | - Validates and auto-fixes common AI-generated patterns for Switch, If, Filter nodes
581 | - Extended support to Summarize, Compare Datasets, Sort, Aggregate, Set, HTML, HTTP Request, and Airtable nodes
582 | - Added comprehensive test coverage with 19 tests for all affected node types
583 | - Provides clear error messages and automatic structure corrections
584 | - **TypeScript Type Safety**: Improved type safety in fixed collection validator
585 | - Replaced all `any` types with proper TypeScript types (`NodeConfig`, `NodeConfigValue`)
586 | - Added type guards for safe property access
587 | - Fixed potential memory leak in `getAllPatterns` by creating deep copies
588 | - Added circular reference protection using `WeakSet` in structure traversal
589 | - **Node Type Normalization**: Fixed inconsistent node type casing
590 | - Normalized `compareDatasets` to `comparedatasets` and `httpRequest` to `httprequest`
591 | - Ensures consistent node type handling across all validation tools
592 | - Maintains backward compatibility with existing workflows
593 |
594 | ### Enhanced
595 | - **Code Review Improvements**: Addressed all code review feedback
596 | - Made output keys deterministic by removing `Math.random()` usage
597 | - Improved error handling with comprehensive null/undefined/array checks
598 | - Enhanced memory safety with proper object cloning
599 | - Added protection against circular references in configuration objects
600 |
601 | ### Testing
602 | - **Comprehensive Test Coverage**: Added extensive tests for fixedCollection validation
603 | - 19 tests covering all 12 affected node types
604 | - Tests for edge cases including empty configs, non-object values, and circular references
605 | - Real-world AI agent pattern tests based on actual ChatGPT/Claude generated configs
606 | - Version compatibility tests across all validation profiles
607 | - TypeScript compilation tests ensuring type safety
608 |
609 | ## [2.9.0] - 2025-08-01
610 |
611 | ### Added
612 | - **n8n Integration with MCP Client Tool Support**: Complete n8n integration enabling n8n-mcp to run as MCP server within n8n workflows
613 | - Full compatibility with n8n's MCP Client Tool node
614 | - Dedicated n8n mode (`N8N_MODE=true`) for optimized operation
615 | - Workflow examples and n8n-friendly tool descriptions
616 | - Quick deployment script (`deploy/quick-deploy-n8n.sh`) for easy setup
617 | - Docker configuration specifically for n8n deployment (`Dockerfile.n8n`, `docker-compose.n8n.yml`)
618 | - Test scripts for n8n integration (`test-n8n-integration.sh`, `test-n8n-mode.sh`)
619 | - **n8n Deployment Documentation**: Comprehensive guide for deploying n8n-MCP with n8n (`docs/N8N_DEPLOYMENT.md`)
620 | - Local testing instructions using `/scripts/test-n8n-mode.sh`
621 | - Production deployment with Docker Compose
622 | - Cloud deployment guide for Hetzner, AWS, and other providers
623 | - n8n MCP Client Tool setup and configuration
624 | - Troubleshooting section with common issues and solutions
625 | - **Protocol Version Negotiation**: Intelligent client detection for n8n compatibility
626 | - Automatically detects n8n clients and uses protocol version 2024-11-05
627 | - Standard MCP clients get the latest version (2025-03-26)
628 | - Improves compatibility with n8n's MCP Client Tool node
629 | - Comprehensive protocol negotiation test suite
630 | - **Comprehensive Parameter Validation**: Enhanced validation for all MCP tools
631 | - Clear, user-friendly error messages for invalid parameters
632 | - Numeric parameter conversion and edge case handling
633 | - 52 new parameter validation tests
634 | - Consistent error format across all tools
635 | - **Session Management**: Improved session handling with comprehensive test coverage
636 | - Fixed memory leak potential with async cleanup
637 | - Better connection close handling
638 | - Enhanced session management tests
639 | - **Dynamic README Version Badge**: Made version badge update automatically from package.json
640 | - Added `update-readme-version.js` script
641 | - Enhanced `sync-runtime-version.js` to update README badges
642 | - Version badge now stays in sync during publish workflow
643 |
644 | ### Fixed
645 | - **Docker Build Optimization**: Fixed Dockerfile.n8n using wrong dependencies
646 | - Now uses `package.runtime.json` instead of full `package.json`
647 | - Reduces build time from 13+ minutes to 1-2 minutes
648 | - Fixes ARM64 build failures due to network timeouts
649 | - Reduces image size from ~1.5GB to ~280MB
650 | - **CI Test Failures**: Resolved Docker entrypoint permission issues
651 | - Updated tests to accept dynamic UID range (10000-59999)
652 | - Enhanced lock file creation with better error recovery
653 | - Fixed TypeScript lint errors in test files
654 | - Fixed flaky performance tests with deterministic versions
655 | - **Schema Validation Issues**: Fixed n8n nested output format compatibility
656 | - Added validation for n8n's nested output workaround
657 | - Fixed schema validation errors with n8n MCP Client Tool
658 | - Enhanced error sanitization for production environments
659 |
660 | ### Changed
661 | - **Memory Management**: Improved session cleanup to prevent memory leaks
662 | - **Error Handling**: Enhanced error sanitization for production environments
663 | - **Docker Security**: Using unpredictable UIDs/GIDs (10000-59999 range) for better security
664 | - **CI/CD Configuration**: Made codecov patch coverage informational to prevent CI failures on infrastructure code
665 | - **Test Scripts**: Enhanced with Docker auto-installation and better user experience
666 | - Added colored output and progress indicators
667 | - Automatic Docker installation for multiple operating systems
668 | - n8n API key flow for management tools
669 |
670 | ### Security
671 | - **Enhanced Docker Security**: Dynamic UID/GID generation for containers
672 | - **Error Sanitization**: Improved error messages to prevent information leakage
673 | - **Permission Handling**: Better permission management for mounted volumes
674 | - **Input Validation**: Comprehensive parameter validation prevents injection attacks
675 |
676 | ## [2.8.3] - 2025-07-31
677 |
678 | ### Fixed
679 | - **Docker User Switching**: Fixed critical issue where user switching was completely broken in Alpine Linux containers
680 | - Added `su-exec` package for proper privilege dropping in Alpine containers
681 | - Fixed broken shell command in entrypoint that used invalid `exec $*` syntax
682 | - Fixed non-existent `printf %q` command in Alpine's BusyBox shell
683 | - Rewrote user switching logic to properly exec processes with nodejs user
684 | - Fixed race condition in database initialization by ensuring lock directory exists
685 | - **Docker Integration Tests**: Fixed failing tests due to Alpine Linux ps command behavior
686 | - Alpine's BusyBox ps shows numeric UIDs instead of usernames for non-system users
687 | - Tests now accept multiple possible values: "nodejs", "1001", or "1" (truncated)
688 | - Added proper process user verification instead of relying on docker exec output
689 | - Added demonstration test showing docker exec vs main process user context
690 |
691 | ### Security
692 | - **Command Injection Prevention**: Added comprehensive input validation in n8n-mcp wrapper
693 | - Whitelist-based argument validation to prevent command injection
694 | - Only allows safe arguments: --port, --host, --verbose, --quiet, --help, --version
695 | - Rejects any arguments containing shell metacharacters or suspicious content
696 | - **Database Initialization**: Added proper file locking to prevent race conditions
697 | - Uses flock for exclusive database initialization
698 | - Prevents multiple containers from corrupting database during simultaneous startup
699 |
700 | ### Testing
701 | - **Docker Test Reliability**: Comprehensive fixes for CI environment compatibility
702 | - Added Docker image build step in test setup
703 | - Fixed environment variable visibility tests to check actual process environment
704 | - Fixed user switching tests to check real process user instead of docker exec context
705 | - All 18 Docker integration tests now pass reliably in CI
706 |
707 | ### Changed
708 | - **Docker Base Image**: Updated su-exec installation in Dockerfile for proper user switching
709 | - **Error Handling**: Improved error messages and logging in Docker entrypoint script
710 |
711 | ## [2.8.2] - 2025-07-31
712 |
713 | ### Added
714 | - **Docker Configuration File Support**: Full support for JSON config files in Docker containers (fixes #105)
715 | - Parse JSON configuration files and safely export as environment variables
716 | - Support for `/app/config.json` mounting in Docker containers
717 | - Secure shell quoting to prevent command injection vulnerabilities
718 | - Dangerous environment variable blocking (PATH, LD_PRELOAD, etc.)
719 | - Key sanitization for invalid environment variable names
720 | - Support for all JSON data types with proper edge case handling
721 |
722 | ### Fixed
723 | - **Docker Server Mode**: Fixed Docker image failing to start in server mode
724 | - Added `n8n-mcp serve` command support in Docker entrypoint
725 | - Properly set HTTP mode when `serve` command is used
726 | - Fixed missing n8n-mcp binary in Docker image
727 |
728 | ### Security
729 | - **Command Injection Prevention**: Comprehensive security hardening for config parsing
730 | - Implemented POSIX-compliant shell quoting without using eval
731 | - Blocked dangerous environment variables that could affect system security
732 | - Added protection against shell metacharacters in configuration values
733 | - Sanitized configuration keys to prevent invalid shell variable names
734 |
735 | ### Testing
736 | - **Docker Configuration Tests**: Added 53 comprehensive tests for Docker config support
737 | - Unit tests for config parsing, security, and edge cases
738 | - Integration tests for Docker entrypoint behavior
739 | - Tests for serve command transformation
740 | - Security-focused tests for injection prevention
741 |
742 | ### Documentation
743 | - Updated Docker documentation with config file mounting examples
744 | - Added troubleshooting guide for Docker configuration issues
745 |
746 | ## [2.8.0] - 2025-07-30
747 |
748 | ### Added
749 | - **Enhanced Test Suite**: Expanded test coverage from 1,182 to 1,356 tests
750 | - **Unit Tests**: Increased from 933 to 1,107 tests across 44 files (was 30)
751 | - Added comprehensive edge case testing for all validators
752 | - Split large test files for better organization and maintainability
753 | - Added test documentation for common patterns and edge cases
754 | - Improved test factory patterns for better test data generation
755 |
756 | ### Fixed
757 | - **All Test Failures**: Achieved 100% test pass rate (was 99.5%)
758 | - Fixed logger tests by properly setting DEBUG environment variable
759 | - Fixed MSW configuration tests with proper environment restoration
760 | - Fixed workflow validator tests by adding proper connections between nodes
761 | - Fixed TypeScript compilation errors with explicit type annotations
762 | - Fixed ValidationResult mocks to include all required properties
763 | - Fixed environment variable handling in tests for better isolation
764 |
765 | ### Enhanced
766 | - **Test Organization**: Restructured test files for better maintainability
767 | - Split config-validator tests into 4 focused files: basic, edge-cases, node-specific, security
768 | - Added dedicated edge case test files for all validators
769 | - Improved test naming convention to "should X when Y" pattern
770 | - Better test isolation with proper setup/teardown
771 |
772 | ### Documentation
773 | - **Test Documentation**: Added comprehensive test guides
774 | - Created test documentation files for common patterns
775 | - Updated test counts in README.md to reflect new test suite
776 | - Added edge case testing guidelines
777 |
778 | ### CI/CD
779 | - **GitHub Actions**: Fixed permission issues
780 | - Added proper permissions for test, benchmark-pr, and publish workflows
781 | - Fixed status write permissions for benchmark comparisons
782 | - Note: Full permissions will take effect after merge to main branch
783 |
784 | ## [2.7.23] - 2025-07-30
785 |
786 | ### Added
787 | - **Comprehensive Testing Infrastructure**: Implemented complete test suite with 1,182 tests
788 | - **933 Unit Tests** across 30 files covering all services, parsers, database, and MCP layers
789 | - **249 Integration Tests** across 14 files for MCP protocol, database operations, and error handling
790 | - **Test Framework**: Vitest with TypeScript, coverage reporting, parallel execution
791 | - **Mock Strategy**: MSW for API mocking, database mocks, MCP SDK test utilities
792 | - **CI/CD**: GitHub Actions workflow with automated testing on all PRs
793 | - **Test Coverage**: Infrastructure in place with lcov, html, and Codecov integration
794 | - **Performance Testing**: Environment-aware thresholds (CI vs local)
795 | - **Database Isolation**: Each test gets its own database for parallel execution
796 |
797 | ### Fixed
798 | - **CI Test Failures**: Resolved all 115 initially failing integration tests
799 | - Fixed MCP response structure: `response.content[0].text` not `response[0].text`
800 | - Fixed `process.exit(0)` in test setup causing Vitest failures
801 | - Fixed database isolation issues for parallel test execution
802 | - Fixed environment-aware performance thresholds
803 | - Fixed MSW setup isolation preventing interference with unit tests
804 | - Fixed empty database handling in CI environment
805 | - Fixed TypeScript lint errors and strict mode compliance
806 |
807 | ### Enhanced
808 | - **Test Architecture**: Complete rewrite for production readiness
809 | - Proper test isolation with no shared state
810 | - Comprehensive custom assertions for MCP responses
811 | - Test data generators and builders for complex scenarios
812 | - Environment configuration for test modes
813 | - VSCode integration for debugging
814 | - Meaningful test organization with AAA pattern
815 |
816 | ### Documentation
817 | - **Testing Documentation**: Complete overhaul to reflect actual implementation
818 | - `docs/testing-architecture.md`: Comprehensive testing guide with real examples
819 | - Documented all 1,182 tests with distribution by component
820 | - Added lessons learned and common issues/solutions
821 | - Updated README with accurate test statistics and badges
822 |
823 | ### Maintenance
824 | - **Cleanup**: Removed 53 development artifacts and test coordination files
825 | - Deleted temporary agent briefings and coordination documents
826 | - Updated .gitignore to prevent future accumulation
827 | - Cleaned up all `FIX_*.md` and `AGENT_*.md` files
828 |
829 | ## [2.7.22] - 2025-07-28
830 |
831 | ### Security
832 | - **Docker base images**: Updated from Node.js 20 Alpine to Node.js 22 LTS Alpine
833 | - Addresses known vulnerabilities in older Alpine images
834 | - Provides better long-term support with Node.js 22 LTS (supported until April 2027)
835 | - All Dockerfiles updated: `Dockerfile`, `Dockerfile.railway`, `Dockerfile.test`
836 | - Docker Compose extractor service updated to use Node.js 22
837 | - Documentation updated to reflect new base image version
838 |
839 | ### Compatibility
840 | - Tested and verified compatibility with Node.js 22 LTS
841 | - All dependencies work correctly with the new Node.js version
842 | - Docker builds complete successfully with improved security posture
843 |
844 | ## [2.7.21] - 2025-07-23
845 |
846 | ### Updated
847 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
848 | - n8n: 1.102.4 → 1.103.2
849 | - n8n-core: 1.101.2 → 1.102.1
850 | - n8n-workflow: 1.99.1 → 1.100.0
851 | - @n8n/n8n-nodes-langchain: 1.101.2 → 1.102.1
852 | - **Node Database**: Rebuilt with 532 nodes from updated n8n packages
853 | - All validation tests passing with updated dependencies
854 |
855 | ## [2.7.20] - 2025-07-18
856 |
857 | ### Fixed
858 | - **Docker container cleanup on session end** (Issue #66)
859 | - Fixed containers not responding to termination signals when Claude Desktop sessions end
860 | - Added proper SIGTERM/SIGINT signal handlers to stdio-wrapper.ts
861 | - Removed problematic trap commands from docker-entrypoint.sh
862 | - Added STOPSIGNAL directive to Dockerfile for explicit signal handling
863 | - Implemented graceful shutdown in MCP server with database cleanup
864 | - Added stdin close detection for proper cleanup when Claude Desktop closes the pipe
865 | - Containers now properly exit with the `--rm` flag, preventing accumulation
866 | - Recommended using `--init` flag in Docker run command for best signal handling
867 |
868 | ### Documentation
869 | - Updated README with container lifecycle management best practices
870 | - Added `--init` flag to all Docker configuration examples
871 | - Added troubleshooting section for container accumulation issues
872 |
873 | ## [2.7.19] - 2025-07-18
874 |
875 | ### Fixed
876 | - **Enhanced node type format normalization** (Issue #74)
877 | - Fixed issue where `n8n-nodes-langchain.chattrigger` (incorrect format) was not being normalized
878 | - Added support for `n8n-nodes-langchain.*` → `nodes-langchain.*` normalization (without @n8n/ prefix)
879 | - Implemented case-insensitive node name matching (e.g., `chattrigger` → `chatTrigger`)
880 | - Added smart camelCase detection for common patterns (trigger, request, sheets, etc.)
881 | - Fixed `get_node_documentation` tool to use same normalization logic as other tools
882 | - All MCP tools now consistently handle various format variations:
883 | - `nodes-langchain.chatTrigger` (correct format)
884 | - `n8n-nodes-langchain.chatTrigger` (package format)
885 | - `n8n-nodes-langchain.chattrigger` (package + wrong case)
886 | - `nodes-langchain.chattrigger` (wrong case only)
887 | - `@n8n/n8n-nodes-langchain.chatTrigger` (full npm format)
888 | - Updated all 7 node lookup locations to use normalized types for alternatives generation
889 | - Enhanced `getNodeTypeAlternatives()` to normalize all generated alternatives
890 |
891 | ## [2.7.18] - 2025-07-18
892 |
893 | ### Fixed
894 | - **Node type prefix normalization for AI agents** (Issue #71)
895 | - AI agents can now use node types directly from n8n workflow exports without manual conversion
896 | - Added automatic normalization: `n8n-nodes-base.httpRequest` → `nodes-base.httpRequest`
897 | - Added automatic normalization: `@n8n/n8n-nodes-langchain.agent` → `nodes-langchain.agent`
898 | - Fixed 9 MCP tools that were failing with full package names:
899 | - `get_node_info`, `get_node_essentials`, `get_node_as_tool_info`
900 | - `search_node_properties`, `validate_node_minimal`, `validate_node_config`
901 | - `get_property_dependencies`, `search_nodes`, `get_node_documentation`
902 | - Maintains backward compatibility - existing short prefixes continue to work
903 | - Created centralized `normalizeNodeType` utility for consistent handling across all tools
904 | - **Health check endpoint** - Fixed incorrect `/health` endpoint usage
905 | - Now correctly uses `/healthz` endpoint which is available on all n8n instances
906 | - Improved error handling with proper fallback to workflow list endpoint
907 | - Fixed axios import for healthz endpoint access
908 | - **n8n_list_workflows pagination clarity** (Issue #54)
909 | - Changed misleading `total` field to `returned` to clarify it's the count of items in current page
910 | - Added `hasMore` boolean flag for clear pagination indication
911 | - Added `_note` field with guidance when more data is available ("More workflows available. Use cursor to get next page.")
912 | - Applied same improvements to `n8n_list_executions` for consistency
913 | - AI agents now correctly understand they need to use pagination instead of assuming limited total workflows
914 |
915 | ### Added
916 | - **Node type utilities** in `src/utils/node-utils.ts`
917 | - `normalizeNodeType()` - Converts full package names to database format
918 | - `getNodeTypeAlternatives()` - Provides fallback options for edge cases
919 | - `getWorkflowNodeType()` - Constructs proper n8n workflow format from database values
920 | - **workflowNodeType field** in all MCP tool responses that return node information
921 | - AI agents now receive both `nodeType` (internal format) and `workflowNodeType` (n8n format)
922 | - Example: `nodeType: "nodes-base.webhook"`, `workflowNodeType: "n8n-nodes-base.webhook"`
923 | - Prevents confusion where AI agents would search nodes and use wrong format in workflows
924 | - Added to: `search_nodes`, `get_node_info`, `get_node_essentials`, `get_node_as_tool_info`, `validate_node_operation`
925 | - **Version information in health check**
926 | - `n8n_health_check` now returns MCP version and supported n8n version
927 | - Added `mcpVersion`, `supportedN8nVersion`, and `versionNote` fields
928 | - Includes instructions for AI agents to inform users about version compatibility
929 | - Note: n8n API currently doesn't expose instance version, so manual verification is required
930 |
931 | ### Performance
932 | - **n8n_list_workflows response size optimization**
933 | - Tool now returns only minimal metadata (id, name, active, dates, tags, nodeCount) instead of full workflow structure
934 | - Reduced response size by ~95% - from potentially thousands of tokens per workflow to ~10 tokens
935 | - Eliminated token limit errors when listing workflows with many nodes
936 | - Updated tool description to clarify it returns "minimal metadata only"
937 | - Users should use `n8n_get_workflow` to fetch full workflow details when needed
938 |
939 | ## [2.7.17] - 2025-07-17
940 |
941 | ### Fixed
942 | - **Removed faulty auto-generated examples from MCP tools** (Issue #60)
943 | - Removed examples from `get_node_essentials` responses that were misleading AI agents
944 | - Removed examples from `validate_node_operation` when validation errors occur
945 | - Examples were showing incorrect configurations (e.g., Slack showing "channel" property instead of required "select" property)
946 | - Tools now focus on validation errors and fix suggestions instead of potentially incorrect examples
947 | - Preserved helpful format hints in `get_node_for_task` (these show input formats like "#general" or URL examples, not node configurations)
948 | - This change reduces confusion and helps AI agents build correct workflows on the first attempt
949 |
950 | ### Changed
951 | - Updated tool documentation to reflect removal of auto-generated examples
952 | - `get_node_essentials` now points users to `validate_node_operation` for working configurations
953 | - Enhanced validation error messages to be more helpful without relying on examples
954 |
955 | ## [2.7.16] - 2025-07-17
956 |
957 | ### Added
958 | - **Comprehensive MCP tools documentation** (Issue #60)
959 | - Documented 30 previously undocumented MCP tools
960 | - Added complete parameter descriptions, examples, and best practices
961 | - Implemented modular documentation system with per-tool files
962 | - Documentation optimized for AI agent consumption (utilitarian approach)
963 | - Added documentation for all n8n management tools (n8n_*)
964 | - Added documentation for workflow validation tools
965 | - Added documentation for template management tools
966 | - Improved `tools_documentation()` to serve as central documentation hub
967 |
968 | ### Enhanced
969 | - **Tool documentation system** completely rewritten for AI optimization
970 | - Each tool now has its own documentation module
971 | - Consistent structure: description, parameters, examples, tips, common errors
972 | - AI-friendly formatting with clear sections and examples
973 | - Reduced redundancy while maintaining completeness
974 |
975 | ## [2.7.15] - 2025-07-15
976 |
977 | ### Fixed
978 | - **HTTP Server URL Handling**: Fixed hardcoded localhost URLs in HTTP server output (Issue #41, #42)
979 | - Added intelligent URL detection that considers BASE_URL, PUBLIC_URL, and proxy headers
980 | - Server now displays correct public URLs when deployed behind reverse proxies
981 | - Added support for X-Forwarded-Proto and X-Forwarded-Host headers when TRUST_PROXY is enabled
982 | - Fixed port display logic to hide standard ports (80/443) in URLs
983 | - Added new GET endpoints (/, /mcp) for better API discovery
984 |
985 | ### Security
986 | - **Host Header Injection Prevention**: Added hostname validation to prevent malicious proxy headers
987 | - Only accepts valid hostnames (alphanumeric, dots, hyphens, optional port)
988 | - Rejects hostnames with paths, usernames, or special characters
989 | - Falls back to safe defaults when invalid headers are detected
990 | - **URL Scheme Validation**: Restricted URL schemes to http/https only
991 | - Blocks dangerous schemes like javascript:, file://, data:
992 | - Validates all configured URLs (BASE_URL, PUBLIC_URL)
993 | - **Information Disclosure**: Removed sensitive environment data from API responses
994 | - Root endpoint no longer exposes internal configuration
995 | - Only shows essential API information
996 |
997 | ### Added
998 | - **URL Detection Utility**: New `url-detector.ts` module for intelligent URL detection
999 | - Prioritizes explicit configuration (BASE_URL/PUBLIC_URL)
1000 | - Falls back to proxy headers when TRUST_PROXY is enabled
1001 | - Uses host/port configuration as final fallback
1002 | - Includes comprehensive security validations
1003 | - **Test Scripts**: Added test scripts for URL configuration and security validation
1004 | - `test-url-configuration.ts`: Tests various URL detection scenarios
1005 | - `test-security.ts`: Validates security fixes for malicious headers
1006 |
1007 | ### Changed
1008 | - **Consistent Versioning**: Fixed version inconsistency between server implementations
1009 | - Both http-server.ts and http-server-single-session.ts now use PROJECT_VERSION
1010 | - Removed hardcoded version strings
1011 | - **HTTP Bridge**: Updated to use HOST/PORT environment variables for default URL construction
1012 | - **Documentation**: Updated HTTP deployment guide with URL configuration section
1013 |
1014 | ## [2.7.14] - 2025-07-15
1015 |
1016 | ### Fixed
1017 | - **Partial Update Tool**: Fixed validation/execution discrepancy that caused "settings must NOT have additional properties" error (Issue #45)
1018 | - Removed logic in `cleanWorkflowForUpdate` that was incorrectly adding default settings to workflows
1019 | - The function now only removes read-only fields without adding any new properties
1020 | - This fixes the issue where partial updates would pass validation but fail during execution
1021 | - Added comprehensive test coverage in `test-issue-45-fix.ts`
1022 |
1023 | ## [2.7.13] - 2025-07-11
1024 |
1025 | ### Fixed
1026 | - **npx Execution**: Fixed WASM file resolution for sql.js when running via `npx n8n-mcp` (Issue #31)
1027 | - Enhanced WASM file locator to try multiple path resolution strategies
1028 | - Added `require.resolve()` for reliable package location in npm environments
1029 | - Made better-sqlite3 an optional dependency to prevent installation failures
1030 | - Improved error messages when sql.js fails to load
1031 | - The package now works correctly with `npx` without any manual configuration
1032 |
1033 | ### Changed
1034 | - **Database Adapter**: Improved path resolution for both local development and npm package contexts
1035 | - Supports various npm installation scenarios (global, local, npx cache)
1036 | - Better fallback handling for sql.js WebAssembly file loading
1037 |
1038 | ## [2.7.12] - 2025-07-10
1039 |
1040 | ### Updated
1041 | - **n8n Dependencies**: Updated to latest versions for compatibility and new features
1042 | - n8n: 1.100.1 → 1.101.1
1043 | - n8n-core: 1.99.0 → 1.100.0
1044 | - n8n-workflow: 1.97.0 → 1.98.0
1045 | - @n8n/n8n-nodes-langchain: 1.99.0 → 1.100.1
1046 | - **Node Database**: Rebuilt with 528 nodes from updated n8n packages
1047 | - All validation tests passing with updated dependencies
1048 |
1049 | ## [2.7.11] - 2025-07-10
1050 |
1051 | ### Enhanced
1052 | - **Token Efficiency**: Significantly reduced MCP tool description lengths for better AI agent performance
1053 | - Documentation tools: Average 129 chars (down from ~250-450)
1054 | - Management tools: Average 93 chars (down from ~200-400)
1055 | - Overall token reduction: ~65-70%
1056 | - Moved detailed documentation to `tools_documentation()` system
1057 | - Only 2 tools exceed 200 chars (list_nodes: 204, n8n_update_partial_workflow: 284)
1058 | - Preserved all essential information while removing redundancy
1059 |
1060 | ### Fixed
1061 | - **search_nodes Tool**: Major improvements to search functionality for AI agents
1062 | - Primary nodes (webhook, httpRequest) now appear first in search results instead of being buried
1063 | - Fixed issue where searching "webhook" returned specialized triggers instead of the main Webhook node
1064 | - Fixed issue where searching "http call" didn't prioritize HTTP Request node
1065 | - Fixed FUZZY mode returning no results for typos like "slak" (lowered threshold from 300 to 200)
1066 | - Removed unnecessary searchInfo messages that appeared on every search
1067 | - Fixed HTTP node type comparison case sensitivity issue
1068 | - Implemented relevance-based ranking with special boosting for primary nodes
1069 | - **search_templates FTS5 Error**: Fixed "no such module: fts5" error in environments without FTS5 support (fixes Claude Desktop issue)
1070 | - Made FTS5 completely optional - detects support at runtime
1071 | - Removed FTS5 from required schema to prevent initialization failures
1072 | - Automatically falls back to LIKE search when FTS5 is unavailable
1073 | - FTS5 tables and triggers created conditionally only if supported
1074 | - Template search now works in ALL SQLite environments
1075 |
1076 | ### Added
1077 | - **FTS5 Full-Text Search**: Added SQLite FTS5 support for faster and more intelligent node searching
1078 | - Automatic fallback to LIKE queries if FTS5 is unavailable
1079 | - Supports advanced search modes: OR (default), AND (all terms required), FUZZY (typo-tolerant)
1080 | - Significantly improves search performance for large databases
1081 | - FUZZY mode now uses edit distance (Levenshtein) for better typo tolerance
1082 | - **FTS5 Detection**: Added runtime detection of FTS5 support
1083 | - `checkFTS5Support()` method in database adapters
1084 | - Conditional initialization of FTS5 features
1085 | - Graceful degradation when FTS5 not available
1086 |
1087 | ## [Unreleased]
1088 |
1089 | ### Fixed
1090 | - **Code Node Documentation**: Corrected information about `$helpers` object and `getWorkflowStaticData` function
1091 | - `$getWorkflowStaticData()` is a standalone function, NOT `$helpers.getWorkflowStaticData()`
1092 | - Updated Code node guide to clarify which functions are standalone vs methods on $helpers
1093 | - Added validation warning when using incorrect `$helpers.getWorkflowStaticData` syntax
1094 | - Based on n8n community feedback and GitHub issues showing this is a common confusion point
1095 |
1096 | ### Added
1097 | - **Expression vs Code Node Clarification**: Added comprehensive documentation about differences between expression and Code node contexts
1098 | - New section "IMPORTANT: Code Node vs Expression Context" explaining key differences
1099 | - Lists expression-only functions not available in Code nodes ($now(), $today(), Tournament template functions)
1100 | - Clarifies different syntax: $('Node Name') vs $node['Node Name']
1101 | - Documents reversed JMESPath parameter order between contexts
1102 | - Added "Expression Functions NOT in Code Nodes" section with alternatives
1103 | - **Enhanced Code Node Validation**: Added new validation checks for common expression/Code node confusion
1104 | - Detects expression syntax {{...}} in Code nodes with clear error message
1105 | - Warns about using $node[] syntax instead of $() in Code nodes
1106 | - Identifies expression-only functions with helpful alternatives
1107 | - Checks for wrong JMESPath parameter order
1108 | - Test script `test-expression-code-validation.ts` to verify validation works correctly
1109 |
1110 | ## [2.7.11] - 2025-07-09
1111 |
1112 | ### Fixed
1113 | - **Issue #26**: Fixed critical issue where AI agents were placing error handling properties inside `parameters` instead of at node level
1114 | - Root cause: AI agents were confused by examples showing `parameters.path` updates and assumed all properties followed the same pattern
1115 | - Error handling properties (`onError`, `retryOnFail`, `maxTries`, `waitBetweenTries`, `alwaysOutputData`) must be placed at the NODE level
1116 | - Other node-level properties (`executeOnce`, `disabled`, `notes`, `notesInFlow`, `credentials`) were previously undocumented for AI agents
1117 | - Updated `n8n_create_workflow` and `n8n_update_partial_workflow` documentation with explicit examples and warnings
1118 | - Verified fix with workflows tGyHrsBNWtaK0inQ, usVP2XRXhI35m3Ts, and swuogdCCmNY7jj71
1119 |
1120 | ### Added
1121 | - **Comprehensive Node-Level Properties Reference** in tools documentation (`tools_documentation()`)
1122 | - Documents ALL available node-level properties with explanations
1123 | - Shows correct placement and usage for each property
1124 | - Provides complete example node configuration
1125 | - Accessible via `tools_documentation({depth: "full"})` for AI agents
1126 | - **Enhanced Workflow Validation** for additional node-level properties
1127 | - Now validates `executeOnce`, `disabled`, `notes`, `notesInFlow` types
1128 | - Checks for misplacement of ALL node-level properties (expanded from 6 to 11)
1129 | - Provides clear error messages with correct examples when properties are misplaced
1130 | - Shows specific fix with example node structure
1131 | - **Test Script** `test-node-level-properties.ts` demonstrating correct usage
1132 | - Shows all node-level properties in proper configuration
1133 | - Demonstrates common mistakes to avoid
1134 | - Validates workflow configurations
1135 | - **Comprehensive Code Node Documentation** in tools_documentation
1136 | - New `code_node_guide` topic with complete reference for JavaScript and Python
1137 | - Covers all built-in variables: $input, $json, $node, $workflow, $execution, $prevNode
1138 | - Documents helper functions: DateTime (Luxon), JMESPath, $helpers methods
1139 | - Includes return format requirements with correct/incorrect examples
1140 | - Security considerations and banned operations
1141 | - Common patterns: data transformation, filtering, aggregation, error handling
1142 | - Code node as AI tool examples
1143 | - Performance best practices and debugging tips
1144 | - **Enhanced Code Node Validation** with n8n-specific patterns
1145 | - Validates return statement presence and format
1146 | - Checks for array of objects with json property
1147 | - Detects common mistakes (returning primitives, missing array wrapper)
1148 | - Validates n8n variable usage ($input, items, $json context)
1149 | - Security checks (eval, exec, require, file system access)
1150 | - Language-specific validation for JavaScript and Python
1151 | - Mode-specific warnings ($json in wrong mode)
1152 | - Async/await pattern validation
1153 | - External library detection with helpful alternatives
1154 | - **Expanded Code Node Examples** in ExampleGenerator
1155 | - Data transformation, aggregation, and filtering examples
1156 | - API integration with error handling
1157 | - Python data processing example
1158 | - Code node as AI tool pattern
1159 | - CSV to JSON transformation
1160 | - All examples include proper return format
1161 | - **New Code Node Task Templates**
1162 | - `custom_ai_tool`: Create custom tools for AI agents
1163 | - `aggregate_data`: Summary statistics from multiple items
1164 | - `batch_process_with_api`: Process items in batches with rate limiting
1165 | - `error_safe_transform`: Robust data transformation with validation
1166 | - `async_data_processing`: Concurrent processing with limits
1167 | - `python_data_analysis`: Statistical analysis using Python
1168 | - All templates include comprehensive error handling
1169 | - **Fixed Misleading Documentation** based on real-world testing:
1170 | - **Crypto Module**: Clarified that `require('crypto')` IS available despite editor warnings
1171 | - **Helper Functions**: Fixed documentation showing `$getWorkflowStaticData()` is standalone, not on $helpers
1172 | - **JMESPath**: Corrected syntax from `jmespath.search()` to `$jmespath()`
1173 | - **Node Access**: Fixed from `$node['Node Name']` to `$('Node Name')`
1174 | - **Python**: Documented `item.json.to_py()` for JsProxy conversion
1175 | - Added comprehensive "Available Functions and Libraries" section
1176 | - Created security examples showing proper crypto usage
1177 | - **JMESPath Numeric Literals**: Added critical documentation about n8n-specific requirement for backticks around numbers in filters
1178 | - Example: `[?age >= \`18\`]` not `[?age >= 18]`
1179 | - Added validation to detect and warn about missing backticks
1180 | - Based on Claude Desktop feedback from workflow testing
1181 | - **Webhook Data Structure**: Fixed common webhook data access gotcha
1182 | - Webhook payload is at `items[0].json.body`, NOT `items[0].json`
1183 | - Added dedicated "Webhook Data Access" section in Code node documentation
1184 | - Created webhook processing example showing correct data access
1185 | - Added validation to detect incorrect webhook data access patterns
1186 | - New task template `process_webhook_data` with complete example
1187 |
1188 | ### Enhanced
1189 | - **MCP Tool Documentation** significantly improved:
1190 | - `n8n_create_workflow` now includes complete node example with all properties
1191 | - `n8n_update_partial_workflow` shows difference between node-level vs parameter updates
1192 | - Added "CRITICAL" warnings about property placement
1193 | - Updated best practices and common pitfalls sections
1194 | - **Workflow Validator** improvements:
1195 | - Expanded property checking from 6 to 11 node-level properties
1196 | - Better error messages showing complete correct structure
1197 | - Type validation for all node-level boolean and string properties
1198 | - **Code Node Validation** enhanced with new checks:
1199 | - Detects incorrect `$helpers.getWorkflowStaticData()` usage
1200 | - Warns about `$helpers` usage without availability check
1201 | - Validates crypto usage with proper require statement
1202 | - All based on common errors found in production workflows
1203 | - **Type Definitions** updated:
1204 | - Added `notesInFlow` to WorkflowNode interface in workflow-validator.ts
1205 | - Fixed credentials type from `Record<string, string>` to `Record<string, unknown>` in n8n-api.ts
1206 | - **NodeSpecificValidators** now includes comprehensive Code node validation
1207 | - Language-specific syntax checks
1208 | - Return format validation with detailed error messages
1209 | - n8n variable usage validation
1210 | - Security pattern detection
1211 | - Error handling recommendations
1212 | - Mode-specific suggestions
1213 | - **Config Validator** improved Code node validation
1214 | - Better return statement detection
1215 | - Enhanced syntax checking for both JavaScript and Python
1216 | - More helpful error messages with examples
1217 | - Detection of common n8n Code node mistakes
1218 | - **Fixed Documentation Inaccuracies** based on user testing and n8n official docs:
1219 | - JMESPath: Corrected syntax to `$jmespath()` instead of `jmespath.search()`
1220 | - Node Access: Fixed to show `$('Node Name')` syntax, not `$node`
1221 | - Python: Documented `_input.all()` and `item.json.to_py()` for JsProxy conversion
1222 | - Python: Added underscore prefix documentation for all built-in variables
1223 | - Validation: Skip property visibility warnings for Code nodes to reduce false positives
1224 |
1225 | ## [2.7.10] - 2025-07-09
1226 |
1227 | ### Documentation Update
1228 | - Added comprehensive documentation on how to update error handling properties using `n8n_update_partial_workflow`
1229 | - Error handling properties can be updated at the node level using the workflow diff engine:
1230 | - `continueOnFail`: boolean - Whether to continue workflow on node failure
1231 | - `onError`: 'continueRegularOutput' | 'continueErrorOutput' | 'stopWorkflow' - Error handling strategy
1232 | - `retryOnFail`: boolean - Whether to retry on failure
1233 | - `maxTries`: number - Maximum retry attempts
1234 | - `waitBetweenTries`: number - Milliseconds to wait between retries
1235 | - `alwaysOutputData`: boolean - Always output data even on error
1236 | - Added test script demonstrating error handling property updates
1237 | - Updated WorkflowNode type to include `onError` property in n8n-api types
1238 | - Workflow diff engine now properly handles all error handling properties
1239 |
1240 | ## [2.7.10] - 2025-07-07
1241 |
1242 | ### Added
1243 | - Enhanced authentication logging for better debugging of client authentication issues
1244 | - Specific error reasons for authentication failures: `no_auth_header`, `invalid_auth_format`, `invalid_token`
1245 | - AUTH_TOKEN_FILE support in single-session HTTP server for consistency
1246 | - Empty token validation to prevent security issues
1247 | - Whitespace trimming for authentication tokens
1248 |
1249 | ### Fixed
1250 | - Issue #22: Improved authentication failure diagnostics for mcp-remote client debugging
1251 | - Issue #16: Fixed AUTH_TOKEN_FILE validation for HTTP mode in Docker production stacks - Docker entrypoint now properly validates and supports AUTH_TOKEN_FILE environment variable
1252 | - Security: Removed token length from logs to prevent information disclosure
1253 |
1254 | ### Security
1255 | - Authentication tokens are now trimmed to handle whitespace edge cases
1256 | - Empty tokens are explicitly rejected with clear error messages
1257 | - Removed sensitive information (token lengths) from authentication logs
1258 |
1259 | ## [2.7.8] - 2025-07-06
1260 |
1261 | ### Added
1262 | - npx support for zero-installation usage - users can now run `npx n8n-mcp` without installing
1263 | - npm package distribution with runtime-only dependencies (8 deps vs 50+ dev deps)
1264 | - Dedicated publish script for npm releases with OTP support
1265 | - Database path resolution supporting npx, global, and local installations
1266 |
1267 | ### Fixed
1268 | - Issue #15: Added npx execution support as requested
1269 | - Removed development dependencies from npm package (reduced from 1GB+ to ~50MB)
1270 | - Node.js version conflicts by excluding n8n dependencies from runtime package
1271 |
1272 | ### Changed
1273 | - npm package now uses package.runtime.json for publishing (no n8n dependencies)
1274 | - Enhanced .gitignore to exclude npm publishing artifacts
1275 | - README now highlights npx as the primary installation method
1276 |
1277 | ## [2.7.5] - 2025-07-06
1278 |
1279 | ### Added
1280 | - AUTH_TOKEN_FILE support for reading authentication tokens from files (Docker secrets compatible) - partial implementation
1281 | - Known Issues section in README documenting Claude Desktop container duplication bug
1282 | - Enhanced authentication documentation in Docker README
1283 |
1284 | ### Fixed
1285 | - Issue #16: AUTH_TOKEN_FILE was documented but not implemented (partially fixed - see v2.7.10 for complete fix)
1286 | - HTTP server now properly supports both AUTH_TOKEN and AUTH_TOKEN_FILE environment variables
1287 |
1288 | ### Changed
1289 | - Authentication logic now checks AUTH_TOKEN first, then falls back to AUTH_TOKEN_FILE
1290 | - Updated Docker documentation to clarify authentication options
1291 |
1292 | ## [2.7.4] - 2025-07-03
1293 |
1294 | ### Changed
1295 | - Renamed `start_here_workflow_guide` tool to `tools_documentation` for better clarity
1296 | - Converted tool output from JSON to LLM-friendly plain text format
1297 | - Made documentation concise by default with "essentials" depth
1298 |
1299 | ### Added
1300 | - `depth` parameter to control documentation detail level ("essentials" or "full")
1301 | - Per-tool documentation - get help for any specific MCP tool
1302 | - Two-tier documentation system:
1303 | - Essentials: Brief description, key parameters, example, performance, tips
1304 | - Full: Complete documentation with all details, examples, best practices
1305 | - Quick reference mode when called without parameters
1306 | - Documentation for 8 commonly used tools
1307 | - Test script for tools documentation (`test:tools-documentation`)
1308 |
1309 | ### Removed
1310 | - Removed duplicate `tools_documentation` tool definition
1311 | - Removed unused `getWorkflowGuide` method (380+ lines)
1312 | - Removed old `handlers-documentation.ts` file
1313 |
1314 | ## [2.7.3] - 2025-07-02
1315 |
1316 | ### Added
1317 | - MCP Tools Documentation system (initial implementation)
1318 | - `tools_documentation` tool for comprehensive MCP tool documentation
1319 | - Documentation includes parameters, examples, best practices, and pitfalls
1320 | - Search tools by keyword functionality
1321 | - Browse tools by category
1322 | - Quick reference guide with workflow patterns
1323 |
1324 | ### Fixed
1325 | - Cleaned up redundant tool definitions
1326 |
1327 | ## [2.7.2] - 2025-07-01
1328 |
1329 | ### Fixed
1330 | - HTTP deployment documentation improvements
1331 | - Docker configuration updates with n8n API options
1332 |
1333 | ### Changed
1334 | - Updated version handling in multiple configuration files
1335 |
1336 | ## [2.7.1] - 2025-06-30
1337 |
1338 | ### Fixed
1339 | - Workflow diff engine edge cases
1340 | - Transactional update processing improvements
1341 |
1342 | ### Added
1343 | - Additional test coverage for diff operations
1344 | - Debug scripts for update operations
1345 |
1346 | ## [2.7.0] - 2025-06-29
1347 |
1348 | ### Added
1349 | - New `n8n_update_partial_workflow` tool for efficient diff-based workflow editing with transactional updates
1350 | - WorkflowDiffEngine for applying targeted edits without sending full workflow JSON (80-90% token savings)
1351 | - 13 diff operations: addNode, removeNode, updateNode, moveNode, enableNode, disableNode, addConnection, removeConnection, updateConnection, updateSettings, updateName, addTag, removeTag
1352 | - Smart node references supporting both node ID and name
1353 | - Transaction safety with validation before applying changes
1354 | - Validation-only mode for testing diff operations
1355 | - Comprehensive test coverage for all diff operations
1356 | - Example guide in `docs/workflow-diff-examples.md`
1357 | - Two-pass processing allowing operations in any order
1358 | - Operation limit of 5 operations per request for reliability
1359 | - `n8n_diagnostic` tool to troubleshoot management tools visibility issues
1360 | - Version utility (`src/utils/version.ts`) for centralized version management
1361 | - Script to sync package.runtime.json version
1362 |
1363 | ### Changed
1364 | - Renamed `n8n_update_workflow` to `n8n_update_full_workflow` to clarify it replaces entire workflow
1365 | - Renamed core MCP files for clarity:
1366 | - `tools-update.ts` → `tools.ts`
1367 | - `server-update.ts` → `server.ts`
1368 | - `http-server-fixed.ts` → `http-server.ts`
1369 | - Updated imports across 21+ files to use new file names
1370 |
1371 | ### Fixed
1372 | - Version mismatch issue where version was hardcoded instead of reading from package.json (GitHub issue #5)
1373 | - MCP validation error by simplifying schema to allow additional properties
1374 | - n8n API validation by removing all read-only fields in cleanWorkflowForUpdate
1375 | - Claude Desktop compatibility by adding additionalProperties: true
1376 | - Removed DEBUG console.log statements from MCP server
1377 |
1378 | ### Removed
1379 | - Legacy HTTP server implementation (`src/http-server.ts`)
1380 | - Unused legacy API client (`src/utils/n8n-client.ts`)
1381 | - Unnecessary file name suffixes (-update, -fixed)
1382 |
1383 | ## [2.6.3] - 2025-06-26
1384 |
1385 | ### Added
1386 | - `n8n_validate_workflow` tool to validate workflows directly from n8n instance by ID
1387 | - Fetches workflow from n8n API and runs comprehensive validation
1388 | - Supports all validation profiles and options
1389 | - Part of complete lifecycle: discover → build → validate → deploy → execute
1390 |
1391 | ## [2.6.2] - 2025-06-26
1392 |
1393 | ### Added
1394 | - Node type validation to verify node types exist in n8n
1395 | - Smart suggestions for common mistakes (e.g., `webhook` → `n8n-nodes-base.webhook`)
1396 | - Minimum viable workflow validation preventing single-node workflows (except webhooks)
1397 | - Empty connection detection for multi-node workflows
1398 | - Helper functions: `getWorkflowStructureExample()` and `getWorkflowFixSuggestions()`
1399 |
1400 | ### Fixed
1401 | - nodes-base prefix detection now catches errors before database lookup
1402 | - Enhanced error messages with clear guidance on proper workflow structure
1403 |
1404 | ## [2.6.1] - 2025-06-26
1405 |
1406 | ### Added
1407 | - typeVersion validation in workflow validator
1408 | - Enforces typeVersion on all versioned nodes
1409 | - Warns on outdated node versions
1410 | - Prevents invalid version numbers
1411 |
1412 | ### Fixed
1413 | - Missing typeVersion errors with correct version suggestions
1414 | - Invalid version detection exceeding maximum supported
1415 |
1416 | ## [2.6.0] - 2025-06-26
1417 |
1418 | ### Added
1419 | - 14 n8n management tools for complete workflow lifecycle management:
1420 | - `n8n_create_workflow` - Create workflows programmatically
1421 | - `n8n_update_workflow` - Update existing workflows
1422 | - `n8n_trigger_webhook_workflow` - Execute workflows via webhooks
1423 | - `n8n_list_executions` - Monitor workflow executions
1424 | - `n8n_health_check` - Check n8n instance connectivity
1425 | - And 9 more workflow and execution management tools
1426 | - Integration with n8n-manager-for-ai-agents functionality
1427 | - Conditional tool registration based on N8N_API_URL and N8N_API_KEY configuration
1428 | - Smart error handling for API limitations
1429 |
1430 | ## [2.5.1] - 2025-06-24
1431 |
1432 | ### Added
1433 | - `get_node_as_tool_info` tool for specific information about using ANY node as an AI tool
1434 | - Enhanced AI tool support with usage guidance
1435 | - Improved start_here_workflow_guide with Claude Project setup
1436 |
1437 | ### Changed
1438 | - Enhanced AI tool detection and documentation
1439 | - Updated documentation to match current state
1440 |
1441 | ## [2.5.0] - 2025-06-24
1442 |
1443 | ### Added
1444 | - Comprehensive workflow validation system:
1445 | - `validate_workflow` - Validate entire workflows before deployment
1446 | - `validate_workflow_connections` - Check workflow structure and connections
1447 | - `validate_workflow_expressions` - Validate all n8n expressions
1448 | - Expression validator for n8n syntax validation
1449 | - AI tool connection validation
1450 | - Phase 2 validation improvements
1451 |
1452 | ## [2.4.2] - 2025-06-24
1453 |
1454 | ### Added
1455 | - Enhanced operation-aware validation system
1456 | - `validate_node_operation` - Verify node configuration with operation awareness
1457 | - `validate_node_minimal` - Quick validation for required fields only
1458 | - Node-specific validation logic
1459 | - Validation profiles support
1460 |
1461 | ### Fixed
1462 | - Validation improvements based on AI agent feedback
1463 |
1464 | ## [2.4.1] - 2025-06-20
1465 |
1466 | ### Added
1467 | - n8n workflow templates integration:
1468 | - `list_node_templates` - Find workflow templates using specific nodes
1469 | - `get_template` - Get complete workflow JSON for import
1470 | - `search_templates` - Search templates by keywords
1471 | - `get_templates_for_task` - Get curated templates for common tasks
1472 | - Template fetching from n8n.io API
1473 | - Robust template fetching with retries
1474 | - Expanded template window from 6 months to 1 year
1475 |
1476 | ### Fixed
1477 | - Made templates available in Docker by removing axios from runtime
1478 | - Template service made optional in Docker environment
1479 | - Non-deterministic CHECK constraint removed from templates table
1480 |
1481 | ## [2.4.0] - 2025-06-18
1482 |
1483 | ### Added
1484 | - AI-optimized tools with 95% size reduction:
1485 | - `get_node_essentials` - Returns only essential properties (10-20) with examples
1486 | - `search_node_properties` - Find specific properties without downloading everything
1487 | - `get_node_for_task` - Get pre-configured node settings for common tasks
1488 | - `list_tasks` - List all available task templates
1489 | - `get_property_dependencies` - Analyze property dependencies and visibility conditions
1490 | - Property filter service with curated essential properties
1491 | - Example generator for common use cases
1492 | - Task templates with pre-configured settings
1493 | - Docker build optimization (82% smaller images, 10x faster builds)
1494 |
1495 | ### Changed
1496 | - Switched to MIT license for wider adoption
1497 | - Optimized Docker builds to exclude n8n dependencies at runtime
1498 | - Improved tool descriptions and added workflow guide tool
1499 |
1500 | ### Fixed
1501 | - Docker build failures in GitHub Actions
1502 | - Claude Desktop stdio communication issues
1503 | - Version array handling in node parser
1504 |
1505 | ### Removed
1506 | - Legacy MCP implementation files
1507 | - n8n dependencies from Docker runtime image
1508 |
1509 | ## [2.3.3] - 2025-06-16
1510 |
1511 | ### Added
1512 | - Smart dependency update system for n8n packages
1513 | - GitHub Actions workflow for automated n8n updates
1514 | - Alternative Renovate configuration
1515 |
1516 | ### Fixed
1517 | - n8n package interdependent version requirements
1518 | - Node type references in validation script
1519 |
1520 | ## [2.3.2] - 2025-06-14
1521 |
1522 | ### Added
1523 | - Single-session HTTP server architecture
1524 | - Direct JSON-RPC implementation for HTTP mode
1525 | - Console output isolation for clean JSON-RPC responses
1526 |
1527 | ### Fixed
1528 | - "stream is not readable" error in HTTP server
1529 | - "Server not initialized" error with StreamableHTTPServerTransport
1530 | - MCP HTTP server stream errors
1531 |
1532 | ## [2.3.1] - 2025-06-13
1533 |
1534 | ### Added
1535 | - HTTP server mode for remote deployment with token authentication
1536 | - MCP-compatible HTTP endpoints
1537 | - Security features: CORS, rate limiting, request size limits
1538 | - Comprehensive HTTP testing scripts
1539 |
1540 | ## [2.3.0] - 2025-06-12
1541 |
1542 | ### Added
1543 | - Universal Node.js compatibility with automatic database adapter fallback
1544 | - Database adapter pattern with BetterSQLiteAdapter and SQLJSAdapter
1545 | - Automatic adapter selection based on environment
1546 | - sql.js persistence layer with debounced saves
1547 |
1548 | ### Changed
1549 | - Database operations now use unified adapter interface
1550 | - Transparent adapter switching for different Node.js versions
1551 |
1552 | ## [2.2.0] - 2025-06-12
1553 |
1554 | ### Added
1555 | - Enhanced node parser with versioned node support
1556 | - Dedicated property extractor for complex node structures
1557 | - Full support for @n8n/n8n-nodes-langchain package
1558 | - AI tool detection (35 tools with usableAsTool property)
1559 |
1560 | ### Changed
1561 | - Major refactor based on IMPLEMENTATION_PLAN.md v2.2
1562 | - Improved property/operation extraction (452/458 nodes have properties)
1563 | - Enhanced documentation mapping
1564 |
1565 | ### Fixed
1566 | - VersionedNodeType handling
1567 | - Documentation mapping issues
1568 | - Property extraction for 98.7% of nodes
1569 |
1570 | ## [2.1.0] - 2025-06-09
1571 |
1572 | ### Added
1573 | - Node extraction scripts for n8n modules
1574 | - Docker setup for n8n module processing
1575 | - Enhanced documentation fetcher
1576 | - Node source extractor utility
1577 |
1578 | ## [2.0.0] - 2025-06-08
1579 |
1580 | ### Added
1581 | - Complete overhaul to enhanced documentation-only MCP server
1582 | - SQLite database with FTS5 for fast searching
1583 | - Comprehensive MCP tools for querying n8n nodes
1584 | - Node documentation service as core component
1585 |
1586 | ### Changed
1587 | - Architecture redesign focusing on documentation serving
1588 | - Removed workflow execution capabilities
1589 | - Simplified to documentation and knowledge serving
1590 |
1591 | ## [1.0.0] - 2025-06-08
1592 |
1593 | ### Added
1594 | - Initial release
1595 | - Basic n8n and MCP integration
1596 | - Core workflow automation features
1597 |
1598 | [2.12.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.11.3...v2.12.0
1599 | [2.11.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.11.2...v2.11.3
1600 | [2.11.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.11.1...v2.11.2
1601 | [2.11.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.11.0...v2.11.1
1602 | [2.11.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.9...v2.11.0
1603 | [2.10.9]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.8...v2.10.9
1604 | [2.10.8]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.5...v2.10.8
1605 | [2.10.5]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.4...v2.10.5
1606 | [2.10.4]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.3...v2.10.4
1607 | [2.10.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.2...v2.10.3
1608 | [2.10.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.1...v2.10.2
1609 | [2.10.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.10.0...v2.10.1
1610 | [2.10.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.9.1...v2.10.0
1611 | [2.9.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.9.0...v2.9.1
1612 | [2.9.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.8.3...v2.9.0
1613 | [2.8.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.8.2...v2.8.3
1614 | [2.8.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.8.0...v2.8.2
1615 | [2.8.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.23...v2.8.0
1616 | [2.7.23]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.22...v2.7.23
1617 | [2.7.22]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.21...v2.7.22
1618 | [2.7.21]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.20...v2.7.21
1619 | [2.7.20]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.19...v2.7.20
1620 | [2.7.19]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.18...v2.7.19
1621 | [2.7.18]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.17...v2.7.18
1622 | [2.7.17]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.16...v2.7.17
1623 | [2.7.16]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.15...v2.7.16
1624 | [2.7.15]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.13...v2.7.15
1625 | [2.7.13]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.12...v2.7.13
1626 | [2.7.12]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.11...v2.7.12
1627 | [2.7.11]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.10...v2.7.11
1628 | [2.7.10]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.8...v2.7.10
1629 | [2.7.8]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.5...v2.7.8
1630 | [2.7.5]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.4...v2.7.5
1631 | [2.7.4]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.3...v2.7.4
1632 | [2.7.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.2...v2.7.3
1633 | [2.7.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.1...v2.7.2
1634 | [2.7.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.7.0...v2.7.1
1635 | [2.7.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.6.3...v2.7.0
1636 | [2.6.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.6.2...v2.6.3
1637 | [2.6.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.6.1...v2.6.2
1638 | [2.6.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.6.0...v2.6.1
1639 | [2.6.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.5.1...v2.6.0
1640 | [2.5.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.5.0...v2.5.1
1641 | [2.5.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.4.2...v2.5.0
1642 | [2.4.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.4.1...v2.4.2
1643 | [2.4.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.4.0...v2.4.1
1644 | [2.4.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.3.3...v2.4.0
1645 | [2.3.3]: https://github.com/czlonkowski/n8n-mcp/compare/v2.3.2...v2.3.3
1646 | [2.3.2]: https://github.com/czlonkowski/n8n-mcp/compare/v2.3.1...v2.3.2
1647 | [2.3.1]: https://github.com/czlonkowski/n8n-mcp/compare/v2.3.0...v2.3.1
1648 | [2.3.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.2.0...v2.3.0
1649 | [2.2.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.1.0...v2.2.0
1650 | [2.1.0]: https://github.com/czlonkowski/n8n-mcp/compare/v2.0.0...v2.1.0
1651 | [2.0.0]: https://github.com/czlonkowski/n8n-mcp/compare/v1.0.0...v2.0.0
1652 | [1.0.0]: https://github.com/czlonkowski/n8n-mcp/releases/tag/v1.0.0
```