Installing via Smithery

Skip to content

You signed in with another tab or window. Reload
to refresh your session. You signed out in another tab or window. Reload
to refresh your session. You switched accounts on another tab or window. Reload
to refresh your session. Dismiss alert

JackKuo666 / medRxiv-MCP-Server Public

• Notifications
  You must be signed in to change notification settings

• Fork 0

• Star 1

🔍 Enable AI assistants to search and access medRxiv papers through a simple MCP interface.

1 star
0 forks
Branches
Tags
Activity

Star

Notifications
You must be signed in to change notification settings

JackKuo666/medRxiv-MCP-Server

main

2 Branches
0 Tags

Go to file

Code

Folders and files

| Name | | Name | Last commit message | Last commit date |
| --- | --- | --- | --- |
| Latest commit
-------------


JackKuo666

update

Mar 18, 2025

63bca9d
 · Mar 18, 2025

History
-------

4 Commits

| | |
| __pycache__ | | __pycache__ | update | Mar 18, 2025 |
| .python-version | | .python-version | Initial commit | Mar 18, 2025 |
| README.md | | README.md | update | Mar 18, 2025 |
| medrxiv_server.py | | medrxiv_server.py | update | Mar 18, 2025 |
| medrxiv_web_search.py | | medrxiv_web_search.py | update | Mar 18, 2025 |
| pyproject.toml | | pyproject.toml | Initial commit | Mar 18, 2025 |
| requirements.txt | | requirements.txt | Initial commit | Mar 18, 2025 |
| View all files | | |

Repository files navigation

medRxiv MCP Server

🔍 Enable AI assistants to search and access medRxiv papers through a simple MCP interface.

The medRxiv MCP Server provides a bridge between AI assistants and medRxiv's preprint repository through the Model Context Protocol (MCP). It allows AI models to search for health sciences preprints and access their content in a programmatic way.

🤝 Contribute • 📝 Report Bug

✨ Core Features

• 🔎 Paper Search: Query medRxiv papers with custom search strings or advanced search parameters ✅
• 🚀 Efficient Retrieval: Fast access to paper metadata ✅
• 📊 Metadata Access: Retrieve detailed metadata for specific papers using DOI ✅
• 📊 Research Support: Facilitate health 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

Installing via Smithery

To install medRxiv Server for Claude Desktop automatically via Smithery
:

claude

npx -y @smithery/cli@latest install @JackKuo666/medrxiv-mcp-server --client claude --config "{}"

Cursor

Paste the following into Settings → Cursor Settings → MCP → Add new server:

• Mac/Linux

npx -y @smithery/cli@latest run @JackKuo666/medrxiv-mcp-server --client cursor --config "{}" 

Windsurf

npx -y @smithery/cli@latest install @JackKuo666/medrxiv-mcp-server --client windsurf --config "{}"

CLine

npx -y @smithery/cli@latest install @JackKuo666/medrxiv-mcp-server --client cline --config "{}"

Installing Manually

Install using uv:

uv tool install medRxiv-mcp-server

For development:

# Clone and set up development environment
git clone https://github.com/JackKuo666/medRxiv-MCP-Server.git
cd medRxiv-MCP-Server

# Create and activate virtual environment
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt

📊 Usage

Start the MCP server:

python medrxiv_server.py

Once the server is running, you can use the provided MCP tools in your AI assistant or application. Here are some examples of how to use the tools:

Example 1: Search for papers using keywords

result = await mcp.use_tool("search_medrxiv_key_words", {
    "key_words": "COVID-19 vaccine efficacy",
    "num_results": 5
})
print(result)

Example 2: Perform an advanced search

result = await mcp.use_tool("search_medrxiv_advanced", {
    "term": "COVID-19",
    "author1": "MacLachlan",
    "start_date": "2020-01-01",
    "end_date": "2023-12-31",
    "num_results": 3
})
print(result)

Example 3: Get metadata for a specific paper

result = await mcp.use_tool("get_medrxiv_metadata", {
    "doi": "10.1101/2025.03.09.25323517"
})
print(result)

These examples demonstrate how to use the three main tools provided by the medRxiv MCP Server. Adjust the parameters as needed for your specific use case.

🛠 MCP Tools

The medRxiv MCP Server provides the following tools:

search_medrxiv_key_words

Search for articles on medRxiv using key words.

Parameters:

• key_words (str): Search query string
• num_results (int, optional): Number of results to return (default: 10)

Returns: List of dictionaries containing article information

search_medrxiv_advanced

Perform an advanced search for articles on medRxiv.

Parameters:

• term (str, optional): General search term
• title (str, optional): Search in title
• author1 (str, optional): First author
• author2 (str, optional): Second author
• abstract_title (str, optional): Search in abstract and title
• text_abstract_title (str, optional): Search in full text, abstract, and title
• section (str, optional): Section of medRxiv
• start_date (str, optional): Start date for search range (format: YYYY-MM-DD)
• end_date (str, optional): End date for search range (format: YYYY-MM-DD)
• num_results (int, optional): Number of results to return (default: 10)

Returns: List of dictionaries containing article information

get_medrxiv_metadata

Fetch metadata for a medRxiv article using its DOI.

Parameters:

• doi (str): DOI of the article

Returns: Dictionary containing article metadata

Usage with Claude Desktop

Add this configuration to your claude_desktop_config.json:

(Mac OS)

{
  "mcpServers": {
    "medrxiv": {
      "command": "python",
      "args": ["-m", "medrxiv-mcp-server"]
      }
  }
}

(Windows version):

{
  "mcpServers": {
    "medrxiv": {
      "command": "C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
      "args": [\
        "-m",\
        "medrxiv-mcp-server"\
      ]
    }
  }
}

Using with Cline

{
  "mcpServers": {
    "medrxiv": {
      "command": "bash",
      "args": [\
        "-c",\
        "source /home/YOUR/PATH/mcp-server-medRxiv/.venv/bin/activate && python /home/YOUR/PATH/mcp-server-medRxiv/medrxiv_server.py"\
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

After restarting Claude Desktop, the following capabilities will be available:

Searching Papers

You can ask Claude to search for papers using queries like:

Can you search medRxiv for recent papers about genomics?

The search will return basic information about matching papers including:

• Paper title

• Authors

• DOI

Getting Paper Details

Once you have a DOI, you can ask for more details:

Can you show me the details for paper 10.1101/003541?

This will return:

• Full paper title

• Authors

• Publication date

• Paper abstract

• Links to available formats (PDF/HTML)

📝 TODO

download_paper

Download a paper and save it locally.

read_paper

Read the content of a downloaded paper.

list_papers

List all downloaded papers.

📝 Research Prompts

The server offers specialized prompts to help analyze academic papers:

Paper Analysis Prompt

A comprehensive workflow for analyzing academic papers that only requires a paper ID:

result = await call_prompt("deep-paper-analysis", {
    "paper_id": "2401.12345"
})

This prompt includes:

• Detailed instructions for using available tools (list_papers, download_paper, read_paper, search_papers)
• A systematic workflow for paper analysis
• Comprehensive analysis structure covering:
  • Executive summary
  • Research context
  • Methodology analysis
  • Results evaluation
  • Practical and theoretical implications
  • Future research directions
  • Broader impacts

📁 Project Structure

• medrxiv_server.py: The main MCP server implementation using FastMCP
• medrxiv_web_search.py: Contains the web scraping logic for searching medRxiv

🔧 Dependencies

• Python 3.10+
• FastMCP
• asyncio
• logging
• requests (for web scraping, used in medrxiv_web_search.py)
• beautifulsoup4 (for web scraping, used in medrxiv_web_search.py)

You can install the required dependencies using:

pip install FastMCP requests beautifulsoup4

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License.

🙏 Acknowledgements

This project is inspired by and built upon the work done in the arxiv-mcp-server
project.

⚠️ Disclaimer

This tool is for research purposes only. Please respect medRxiv's terms of service and use this tool responsibly.

About

🔍 Enable AI assistants to search and access medRxiv papers through a simple MCP interface.

Resources

Readme

Activity

Stars

1 star

Watchers

1 watching

Forks

0 forks

Report repository

Releases

No releases published

Packages 0

No packages published

Languages

• Python 100.0%

You can’t perform that action at this time.