Pubmed MCP Server

🚀 PubMed MCP Server

This repository contains an MCP server that uses the Entrez module of BioPython to search for PubMed article abstracts. It leverages the FastMCP framework to provide asynchronous search capabilities.

🚀 Quick Start

✨ Features

• Search PubMed: Query articles based on keywords.
• Get Abstracts: Retrieve abstracts of articles returned by PubMed.
• Asynchronous Operations: Use asynchronous execution (via asyncio.to_thread) to avoid blocking the server.

📦 Installation

Prerequisites

• Python 3.8 or higher
• mcp[cli]
• BioPython

Setup Steps

1. Clone the repository:

git clone PubMed-MCP-Server.git
cd PubMed-MCP-Server

2. Install dependencies: Use uv to install the required packages:

uv add -r requirements.txt

3. Configure Entrez email: Ensure a valid email address is set in the code (in main.py):

Entrez.email = "give an email address"

💻 Usage Examples

Running the Server

Start the PubMed MCP server by running the following command:

uv run main.py

This command uses the uv command-line tool to start the server (as you configured).

Configuring the MCP Client

To configure the MCP client to connect to the PubMed MCP server, create or update your config.json file as follows:

{
  "mcpServers": {
    "pubmed": {
      "command": "C:/Users/codingaslu/.local/bin/uv",
      "args": [
        "--directory",
        "C:/Users/codingaslu/OneDrive/Desktop/pubmed-mcp-server",
        "run",
        "main.py"
      ]
    }
  }
}

Configuration Explanation

• command:
  The full path to the command-line tool for running the MCP server (in this case, uv).
• args:
  • --directory: Specify the root directory where the server is located.
  • "C:/Users/aiany/OneDrive/Desktop/YT Video/pubmed-mcp-server": The path to the server's root directory.
  • "run" and "main.py": The command and entry point for starting the PubMed MCP server.

Basic Usage

Once the server is running and the MCP client is configured, you can use the provided tool:

• Tool: search_pubmed
• Parameters:
  • query: The search term in PubMed (default is "endocarditis").
  • max_results: The maximum number of articles to retrieve (default is 10).

Example usage:

search_pubmed(query="endocarditis", max_results=10)

This will return a string containing abstracts separated by line breaks.

📄 License

This project is licensed under the MIT License.