# Directory Structure
```
├── .gitignore
├── .python-version
├── biorxiv_server.py
├── biorxiv_web_search.py
├── pyproject.toml
├── README.md
└── requirements.txt
```
# Files
--------------------------------------------------------------------------------
/.python-version:
--------------------------------------------------------------------------------
```
3.10
```
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
```
# Python-generated files
__pycache__/
*.py[oc]
build/
dist/
wheels/
*.egg-info
# Virtual environments
.venv
```
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
```markdown
# bioRxiv MCP Server
🔍 Enable AI assistants to search and access bioRxiv papers through a simple MCP interface.
The bioRxiv MCP Server provides a bridge between AI assistants and bioRxiv's preprint repository through the Model Context Protocol (MCP). It allows AI models to search for biology preprints and access their metadata in a programmatic way.
🤝 Contribute • 📝 Report Bug
## ✨ Core Features
- 🔎 Paper Search: Query bioRxiv papers with keywords or advanced search ✅
- 🚀 Efficient Retrieval: Fast access to paper metadata ✅
- 📊 Metadata Access: Retrieve detailed metadata for specific papers ✅
- 📊 Research Support: Facilitate biological sciences research and analysis ✅
- 📄 Paper Access: Download and read paper content 📝
- 📋 Paper Listing: View all downloaded papers 📝
- 🗃️ Local Storage: Papers are saved locally for faster access 📝
- 📝 Research Prompts: A set of specialized prompts for paper analysis 📝
## 🚀 Quick Start
### Prerequisites
- Python 3.10+
- FastMCP library
### Installation
1. Clone the repository:
```
git clone https://github.com/JackKuo666/bioRxiv-MCP-Server.git
cd bioRxiv-MCP-Server
```
2. Install the required dependencies:
```
pip install -r requirements.txt
```
### Installing via Smithery
To install bioRxiv Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@JackKuo666/biorxiv-mcp-server):
#### claude
```bash
npx -y @smithery/cli@latest install @JackKuo666/biorxiv-mcp-server --client claude --config "{}"
```
#### Cursor
Paste the following into Settings → Cursor Settings → MCP → Add new server:
- Mac/Linux
```s
npx -y @smithery/cli@latest run @JackKuo666/biorxiv-mcp-server --client cursor --config "{}"
```
#### Windsurf
```sh
npx -y @smithery/cli@latest install @JackKuo666/biorxiv-mcp-server --client windsurf --config "{}"
```
#### CLine
```sh
npx -y @smithery/cli@latest install @JackKuo666/biorxiv-mcp-server --client cline --config "{}"
```
#### Usage with Claude Desktop
Add this configuration to your `claude_desktop_config.json`:
(Mac OS)
```json
{
"mcpServers": {
"biorxiv": {
"command": "python",
"args": ["-m", "biorxiv-mcp-server"]
}
}
}
```
(Windows version):
```json
{
"mcpServers": {
"biorxiv": {
"command": "C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
"args": [
"-m",
"biorxiv-mcp-server"
]
}
}
}
```
Using with Cline
```json
{
"mcpServers": {
"biorxiv": {
"command": "bash",
"args": [
"-c",
"source /home/YOUR/PATH/mcp-server-bioRxiv/.venv/bin/activate && python /home/YOUR/PATH/mcp-server-bioRxiv/biorxiv_server.py"
],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}
```
## 📊 Usage
Start the MCP server:
```bash
python biorxiv_server.py
```
## 🛠 MCP Tools
The bioRxiv MCP Server provides the following tools:
1. `search_biorxiv_key_words`: Search for articles on bioRxiv using keywords.
2. `search_biorxiv_advanced`: Perform an advanced search for articles on bioRxiv with multiple parameters.
3. `get_biorxiv_metadata`: Fetch metadata for a bioRxiv article using its DOI.
### Searching Papers
You can ask the AI assistant to search for papers using queries like:
```
Can you search bioRxiv for recent papers about genomics?
```
### Getting Paper Details
Once you have a DOI, you can ask for more details:
```
Can you show me the metadata for the paper with DOI 10.1101/123456?
```
## 📁 Project Structure
- `biorxiv_server.py`: The main MCP server implementation using FastMCP
- `biorxiv_web_search.py`: Contains the web scraping logic for searching bioRxiv
## 🔧 Dependencies
- Python 3.10+
- FastMCP
- asyncio
- logging
## 🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## 📄 License
This project is licensed under the MIT License.
## ⚠️ Disclaimer
This tool is for research purposes only. Please respect bioRxiv's terms of service and use this tool responsibly.
```
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
```
requests
bs4
mcp
```
--------------------------------------------------------------------------------
/pyproject.toml:
--------------------------------------------------------------------------------
```toml
[project]
name = "mcp-server-bioRxiv"
version = "0.1.0"
description = "An MCP server for searching and retrieving articles from bioRxiv"
readme = "README.md"
requires-python = ">=3.10"
dependencies = [
"mcp[cli]>=1.4.1",
"requests>=2.25.1",
"beautifulsoup4>=4.9.3",
]
```
--------------------------------------------------------------------------------
/biorxiv_server.py:
--------------------------------------------------------------------------------
```python
from typing import Any, List, Dict, Optional
import asyncio
import logging
from mcp.server.fastmcp import FastMCP
from biorxiv_web_search import search_key_words, search_advanced, doi_get_biorxiv_metadata
# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
# Initialize FastMCP server
mcp = FastMCP("biorxiv")
@mcp.tool()
async def search_biorxiv_key_words(key_words: str, num_results: int = 10) -> List[Dict[str, Any]]:
logging.info(f"Searching for articles with key words: {key_words}, num_results: {num_results}")
"""
Search for articles on bioRxiv using key words.
Args:
key_words: Search query string
num_results: Number of results to return (default: 10)
Returns:
List of dictionaries containing article information
"""
try:
results = await asyncio.to_thread(search_key_words, key_words, num_results)
return results
except Exception as e:
return [{"error": f"An error occurred while searching: {str(e)}"}]
@mcp.tool()
async def search_biorxiv_advanced(
term: Optional[str] = None,
title: Optional[str] = None,
author1: Optional[str] = None,
author2: Optional[str] = None,
abstract_title: Optional[str] = None,
text_abstract_title: Optional[str] = None,
section: Optional[str] = None,
start_date: Optional[str] = None,
end_date: Optional[str] = None,
num_results: int = 10
) -> List[Dict[str, Any]]:
logging.info(f"Performing advanced search with parameters: {locals()}")
"""
Perform an advanced search for articles on bioRxiv.
Args:
term: General search term
title: Search in title
author1: First author
author2: Second author
abstract_title: Search in abstract and title
text_abstract_title: Search in full text, abstract, and title
section: Section of bioRxiv
start_date: Start date for search range (format: YYYY-MM-DD)
end_date: End date for search range (format: YYYY-MM-DD)
num_results: Number of results to return (default: 10)
Returns:
List of dictionaries containing article information
"""
try:
results = await asyncio.to_thread(
search_advanced,
term, title, author1, author2, abstract_title, text_abstract_title,
section, start_date, end_date, num_results
)
return results
except Exception as e:
return [{"error": f"An error occurred while performing advanced search: {str(e)}"}]
@mcp.tool()
async def get_biorxiv_metadata(doi: str) -> Dict[str, Any]:
logging.info(f"Fetching metadata for DOI: {doi}")
"""
Fetch metadata for a bioRxiv article using its DOI.
Args:
doi: DOI of the article
Returns:
Dictionary containing article metadata
"""
try:
metadata = await asyncio.to_thread(doi_get_biorxiv_metadata, doi)
return metadata if metadata else {"error": f"No metadata found for DOI: {doi}"}
except Exception as e:
return {"error": f"An error occurred while fetching metadata: {str(e)}"}
if __name__ == "__main__":
logging.info("Starting bioRxiv MCP server")
# Initialize and run the server
mcp.run(transport='stdio')
```
--------------------------------------------------------------------------------
/biorxiv_web_search.py:
--------------------------------------------------------------------------------
```python
import requests
from bs4 import BeautifulSoup
from urllib.parse import quote
def generate_biorxiv_search_url(term=None, title=None, author1=None, author2=None, abstract_title=None,
text_abstract_title=None, journal_code="biorxiv", section=None,
start_date=None, end_date=None, num_results=10, sort="relevance-rank"):
"""根据用户输入的字段生成 bioRxiv 搜索 URL"""
base_url = "https://www.biorxiv.org/search/"
query_parts = []
if term:
query_parts.append(f"{quote(term)}")
if title:
query_parts.append(f"title%3A{quote(title)} title_flags%3Amatch-all")
if author1:
query_parts.append(f"author1%3A{quote(author1)}")
if author2:
query_parts.append(f"author2%3A{quote(author2)}")
if abstract_title:
query_parts.append(f"abstract_title%3A{quote(abstract_title)} abstract_title_flags%3Amatch-all")
if text_abstract_title:
query_parts.append(f"text_abstract_title%3A{quote(text_abstract_title)} text_abstract_title_flags%3Amatch-all")
if journal_code:
query_parts.append(f"jcode%3A{quote(journal_code)}")
if section:
query_parts.append(f"toc_section%3A{quote(section)}")
if start_date and end_date:
query_parts.append(f"limit_from%3A{start_date} limit_to%3A{end_date}")
query_parts.append(f"numresults%3A{num_results}")
query_parts.append(f"sort%3A{quote(sort)} format_result%3Astandard")
return base_url + "%20".join(query_parts)
def scrape_biorxiv_results(search_url):
"""从 bioRxiv 搜索结果页面解析文章信息，包括 DOI"""
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'
}
response = requests.get(search_url, headers=headers)
if response.status_code == 200:
soup = BeautifulSoup(response.text, 'html.parser')
articles = soup.find_all('li', class_='search-result')
results = []
for article in articles:
title_tag = article.find('span', class_='highwire-cite-title')
title = title_tag.text.strip() if title_tag else "No title"
authors_tag = article.find('span', class_='highwire-citation-authors')
authors = authors_tag.text.strip() if authors_tag else "No authors"
abstract_tag = article.find('div', class_='highwire-cite-snippet')
abstract = abstract_tag.text.strip() if abstract_tag else "No abstract"
link_tag = article.find('a', class_='highwire-cite-linked-title')
link = "https://www.biorxiv.org" + link_tag['href'] if link_tag else "No link"
doi_tag = article.find('span', class_='highwire-cite-metadata-doi')
doi_link = doi_tag.text.strip().replace("doi:", "").strip() if doi_tag else "No DOI"
metadata = {}
result = {
"Title": title,
"Authors": authors,
"DOI_link": doi_link,
"Link": link
}
if doi_link != "No DOI":
metadata = doi_get_biorxiv_metadata(doi_link.replace("https://doi.org/", ""))
if metadata:
result.update(metadata)
results.append(result)
return results
else:
print(f"Error: Unable to fetch data (status code: {response.status_code})")
return None
def doi_get_biorxiv_metadata(doi, server="biorxiv"):
"""使用 bioRxiv API 通过 DOI 获取文章的详细元数据"""
url = f"https://api.biorxiv.org/details/{server}/{doi}/na/json"
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'
}
response = requests.get(url, headers=headers)
if response.status_code == 200:
data = response.json()
if 'collection' in data and len(data['collection']) > 0:
article = data['collection'][0]
return {
"DOI": article.get("doi", "No DOI"),
"Title": article.get("title", "No title"),
"Authors": article.get("authors", "No authors"),
"Corresponding Author": article.get("author_corresponding", "No corresponding author"),
"Corresponding Institution": article.get("author_corresponding_institution", "No institution"),
"Date": article.get("date", "No date"),
"Version": article.get("version", "No version"),
"Category": article.get("category", "No category"),
"JATS XML Path": article.get("jats xml path", "No XML path"),
"Abstract": article.get("abstract", "No abstract")
}
else:
print("No data found for DOI:", doi)
return None
else:
print(f"Error: Unable to fetch metadata (status code: {response.status_code})")
return None
def search_key_words(key_words, num_results=10):
# 生成搜索 URL
search_url = generate_biorxiv_search_url(term=key_words, num_results=num_results)
print("Generated URL:", search_url)
# 获取并解析搜索结果
articles = scrape_biorxiv_results(search_url)
return articles
def search_advanced(term, title, author1, author2, abstract_title, text_abstract_title, section, start_date, end_date, num_results):
# 生成搜索 URL
search_url = generate_biorxiv_search_url(term, title=title, author1=author1, author2=author2,
abstract_title=abstract_title,
text_abstract_title=text_abstract_title,
section=section, start_date=start_date,
end_date=end_date, num_results=num_results)
print("Generated URL:", search_url)
# 获取并解析搜索结果
articles = scrape_biorxiv_results(search_url)
return articles
if __name__ == "__main__":
# 1. search_key_words
key_words = "COVID-19"
articles = search_key_words(key_words, num_results=5)
print(articles)
# 2. search_advanced
# 示例：用户输入搜索参数
term = "CRISPR"
title = "CRISPR"
author1 = "Doudna"
author2 = None
abstract_title = "genome"
text_abstract_title = None
section = "New Results"
start_date = "2025-02-27"
end_date = "2025-03-18"
num_results = 5
articles = search_advanced(term, title, author1, author2, abstract_title, text_abstract_title, section, start_date, end_date, num_results)
print(articles)
# 3. doi get biorxiv metadata
doi = "10.1101/2024.06.25.600517"
metadata = doi_get_biorxiv_metadata(doi)
print(metadata)
```