# Directory Structure
```
├── .github
│ └── FUNDING.yml
├── .gitignore
├── LICENSE
├── mcp.json
├── package.json
├── README.md
├── src
│ ├── .DS_Store
│ ├── cli.ts
│ └── index.ts
└── tsconfig.json
```
# Files
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
```
# Dependencies
node_modules/
# Compiled output
dist/
# Logs
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# Environment variables
.env
# IDE
.idea/
.vscode/
*.swp
*.swo
# OS
.DS_Store
Thumbs.db
```
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
```markdown
# Ollama MCP Server
An MCP (Model Context Protocol) server for Ollama that enables seamless integration between Ollama's local LLM models and MCP-compatible applications like Claude Desktop.
## Features
- List available Ollama models
- Pull new models from Ollama
- Chat with models using Ollama's chat API
- Get detailed model information
- Automatic port management
- Environment variable configuration
## Prerequisites
- Node.js (v16 or higher)
- npm
- Ollama installed and running locally
## Installation
### Manual Installation
Install globally via npm:
```bash
npm install -g @rawveg/ollama-mcp
```
### Installing in Other MCP Applications
To install the Ollama MCP Server in other MCP-compatible applications (like Cline or Claude Desktop), add the following configuration to your application's MCP settings file:
```json
{
"mcpServers": {
"@rawveg/ollama-mcp": {
"command": "npx",
"args": [
"-y",
"@rawveg/ollama-mcp"
]
}
}
}
```
The settings file location varies by application:
- Claude Desktop: `claude_desktop_config.json` in the Claude app data directory
- Cline: `cline_mcp_settings.json` in the VS Code global storage
## Usage
### Starting the Server
Simply run:
```bash
ollama-mcp
```
The server will start on port 3456 by default. You can specify a different port using the PORT environment variable:
```bash
PORT=3457 ollama-mcp
```
### Environment Variables
- `PORT`: Server port (default: 3456). Can be used when running directly:
```bash
# When running directly
PORT=3457 ollama-mcp
```
- `OLLAMA_API`: Ollama API endpoint (default: http://localhost:11434)
### API Endpoints
- `GET /models` - List available models
- `POST /models/pull` - Pull a new model
- `POST /chat` - Chat with a model
- `GET /models/:name` - Get model details
## Development
1. Clone the repository:
```bash
git clone https://github.com/rawveg/ollama-mcp.git
cd ollama-mcp
```
2. Install dependencies:
```bash
npm install
```
3. Build the project:
```bash
npm run build
```
4. Start the server:
```bash
npm start
```
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
However, this does **not** grant permission to incorporate this project into third-party services or commercial platforms without prior discussion and agreement. While I previously accepted contributions (such as a Dockerfile and related README updates) to support integration with services like **Smithery**, recent actions by a similar service — **Glama** — have required a reassessment of this policy.
Glama has chosen to include open-source MCP projects in their commercial offering without notice or consent, and subsequently created issue requests asking maintainers to perform unpaid work to ensure compatibility with *their* platform. This behaviour — leveraging community labour for profit without dialogue or compensation — is not only inconsiderate, but **ethically problematic**.
As a result, and to protect the integrity of this project and its contributors, the licence has been updated to the **GNU Affero General Public License v3.0 (AGPL-3.0)**. This change ensures that any use of the software — particularly in **commercial or service-based platforms** — must remain fully compliant with the AGPL's terms **and** obtain a separate commercial licence. Merely linking to the original source is not sufficient where the project is being **actively monetised**. If you wish to include this project in a commercial offering, please get in touch **first** to discuss licensing terms.
## License
AGPL v3.0
## Star History
[](https://www.star-history.com/#rawveg/ollama-mcp&Date)
## Related
- [Ollama](https://ollama.ai)
- [Model Context Protocol](https://github.com/anthropics/model-context-protocol)
This project was previously MIT-licensed. As of 20th April 2025, it is now licensed under AGPL-3.0 to prevent unauthorised commercial exploitation. If your use of this project predates this change, please refer to the relevant Git tag or commit for the applicable licence.
```
--------------------------------------------------------------------------------
/tsconfig.json:
--------------------------------------------------------------------------------
```json
{
"compilerOptions": {
"target": "ES2020",
"module": "NodeNext",
"moduleResolution": "NodeNext",
"outDir": "./dist",
"rootDir": "./src",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"forceConsistentCasingInFileNames": true
},
"include": ["src/**/*"],
"exclude": ["node_modules", "dist"]
}
```
--------------------------------------------------------------------------------
/package.json:
--------------------------------------------------------------------------------
```json
{
"name": "@rawveg/ollama-mcp",
"version": "1.0.9",
"type": "module",
"description": "MCP Server for Ollama integration",
"main": "dist/index.js",
"bin": {
"ollama-mcp": "./dist/cli.js"
},
"files": [
"dist",
"mcp.json"
],
"scripts": {
"build": "tsc && chmod +x dist/cli.js",
"start": "node dist/cli.js",
"prepare": "npm run build"
},
"repository": {
"type": "git",
"url": "git+https://github.com/rawveg/ollama-mcp.git"
},
"keywords": [
"ollama",
"mcp",
"ai",
"claude"
],
"author": "tigreen",
"license": "AGPL-3.0-only",
"dependencies": {
"express": "^4.18.2",
"node-fetch": "^3.3.2"
},
"devDependencies": {
"@types/express": "^4.17.21",
"@types/node": "^20.11.19",
"typescript": "^5.3.3"
}
}
```
--------------------------------------------------------------------------------
/.github/FUNDING.yml:
--------------------------------------------------------------------------------
```yaml
# These are supported funding model platforms
github: rawveg
patreon: # Replace with a single Patreon username
open_collective: # Replace with a single Open Collective username
ko_fi: # Replace with a single Ko-fi username
tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
liberapay: # Replace with a single Liberapay username
issuehunt: # Replace with a single IssueHunt username
lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
polar: # Replace with a single Polar username
buy_me_a_coffee: rawveg
thanks_dev: # Replace with a single thanks.dev username
custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']
```
--------------------------------------------------------------------------------
/src/cli.ts:
--------------------------------------------------------------------------------
```typescript
#!/usr/bin/env node
/**
* @license
* Copyright (c) [Your Name or Organisation] [Year]
*
* This file is part of [Project Name].
*
* [Project Name] is licensed under the GNU Affero General Public License v3.0.
* You may obtain a copy of the license at https://www.gnu.org/licenses/agpl-3.0.html
*
* Unless required by applicable law or agreed to in writing, software distributed
* under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied.
*
* See the License for the specific language governing permissions and limitations.
*/
import { OllamaMCPServer } from './index.js';
const port = parseInt(process.env.PORT || '3456', 10);
const ollamaApi = process.env.OLLAMA_API || 'http://localhost:11434';
const server = new OllamaMCPServer(ollamaApi);
server.start(port).catch((error: Error) => {
console.error('Failed to start server:', error);
process.exit(1);
});
// Handle graceful shutdown
process.on('SIGTERM', () => {
server.stop().then(() => process.exit(0));
});
process.on('SIGINT', () => {
server.stop().then(() => process.exit(0));
});
```
--------------------------------------------------------------------------------
/mcp.json:
--------------------------------------------------------------------------------
```json
{
"name": "ollama-mcp",
"version": "1.0.3",
"type": "tool",
"tools": [
{
"name": "list_ollama_models",
"description": "List all available Ollama models",
"route": {
"path": "/models",
"method": "GET"
},
"parameters": {
"type": "object",
"properties": {}
}
},
{
"name": "pull_ollama_model",
"description": "Pull a new Ollama model",
"route": {
"path": "/models/pull",
"method": "POST"
},
"parameters": {
"type": "object",
"required": ["name"],
"properties": {
"name": {
"type": "string",
"description": "Name of the model to pull"
}
}
}
},
{
"name": "chat_with_ollama",
"description": "Chat with an Ollama model",
"route": {
"path": "/chat",
"method": "POST"
},
"parameters": {
"type": "object",
"required": ["model", "messages"],
"properties": {
"model": {
"type": "string",
"description": "Name of the model to chat with"
},
"messages": {
"type": "array",
"description": "Array of chat messages",
"items": {
"type": "object",
"required": ["role", "content"],
"properties": {
"role": {
"type": "string",
"enum": ["system", "user", "assistant"],
"description": "Role of the message sender"
},
"content": {
"type": "string",
"description": "Content of the message"
}
}
}
}
}
}
},
{
"name": "get_ollama_model_info",
"description": "Get information about a specific Ollama model",
"route": {
"path": "/models/:name",
"method": "GET"
},
"parameters": {
"type": "object",
"required": ["name"],
"properties": {
"name": {
"type": "string",
"description": "Name of the model to get information about"
}
}
}
}
],
"env": {
"PORT": {
"type": "number",
"default": 3456,
"description": "Port to run the server on"
},
"OLLAMA_API": {
"type": "string",
"default": "http://localhost:11434",
"description": "Ollama API endpoint"
}
}
}
```
--------------------------------------------------------------------------------
/src/index.ts:
--------------------------------------------------------------------------------
```typescript
// src/index.ts
/**
* @license
* Copyright (c) [Your Name or Organisation] [Year]
*
* This file is part of [Project Name].
*
* [Project Name] is licensed under the GNU Affero General Public License v3.0.
* You may obtain a copy of the license at https://www.gnu.org/licenses/agpl-3.0.html
*
* Unless required by applicable law or agreed to in writing, software distributed
* under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied.
*
* See the License for the specific language governing permissions and limitations.
*/
import express from 'express';
import fetch from 'node-fetch';
import type { Request, Response } from 'express';
export class OllamaMCPServer {
private app = express();
private server: any;
private ollamaApi: string;
constructor(ollamaApi: string = 'http://localhost:11434') {
this.ollamaApi = ollamaApi;
this.setupRoutes();
}
private setupRoutes() {
this.app.use(express.json());
this.app.get('/models', this.listModels.bind(this));
this.app.post('/models/pull', this.pullModel.bind(this));
this.app.post('/chat', this.chat.bind(this));
this.app.get('/models/:name', this.getModelInfo.bind(this));
}
private async listModels(req: Request, res: Response) {
try {
const response = await fetch(`${this.ollamaApi}/api/tags`);
const data = await response.json();
res.json(data);
} catch (error) {
res.status(500).json({ error: String(error) });
}
}
private async pullModel(req: Request, res: Response) {
const { name } = req.body;
if (!name) {
return res.status(400).json({ error: 'Model name is required' });
}
try {
const response = await fetch(`${this.ollamaApi}/api/pull`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ name })
});
const data = await response.json();
res.json(data);
} catch (error) {
res.status(500).json({ error: String(error) });
}
}
private async chat(req: Request, res: Response) {
const { model, messages } = req.body;
if (!model || !messages) {
return res.status(400).json({ error: 'Model and messages are required' });
}
try {
const response = await fetch(`${this.ollamaApi}/api/chat`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
model,
messages,
stream: false
})
});
const data = await response.json();
res.json(data);
} catch (error) {
res.status(500).json({ error: String(error) });
}
}
private async getModelInfo(req: Request, res: Response) {
const { name } = req.params;
try {
const response = await fetch(`${this.ollamaApi}/api/show`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ name })
});
const data = await response.json();
res.json(data);
} catch (error) {
res.status(500).json({ error: String(error) });
}
}
public start(port: number = 3456): Promise<void> {
return new Promise((resolve, reject) => {
try {
this.server = this.app.listen(port, () => {
console.log(`Ollama MCP Server running on port ${port}`);
resolve();
});
this.server.on('error', (error: Error & { code?: string }) => {
if (error.code === 'EADDRINUSE') {
reject(new Error(`Port ${port} is already in use`));
} else {
reject(error);
}
});
} catch (error) {
reject(error);
}
});
}
public stop(): Promise<void> {
return new Promise((resolve, reject) => {
if (this.server) {
this.server.close((err?: Error) => {
if (err) reject(err);
else resolve();
});
} else {
resolve();
}
});
}
}
export default OllamaMCPServer;
```