Back to MCP Catalog

PubMed Research Access MCP Server

Knowledge & MemoryPython
Search and access medical research papers from PubMed database
Available Tools

search_pubmed

Search PubMed database using keywords and return matching articles

get_article_abstract

Retrieve the abstract for a specific PubMed article

get_article_full_text

Download full text content for open access articles available on PubMed

PubMed Research Access provides an interface to search and retrieve medical research papers from the PubMed database through the NCBI Entrez API. This MCP allows AI assistants to search for scientific articles using keywords, access abstracts, and download full-text content for open access articles. The tool returns XML-formatted full text when available, which provides AI assistants with additional information about document structure. This makes it particularly valuable for research tasks requiring access to medical literature, enabling more informed responses based on peer-reviewed scientific content.

Overview

PubMed Research Access is an MCP server that connects to the PubMed database through the NCBI Entrez API, allowing AI assistants to search and retrieve medical research papers. This tool is particularly useful for research tasks requiring access to scientific medical literature.

Installation

Prerequisites

Before installing, you'll need:

  • Python installed on your system
  • An email address to provide to NCBI (required)
  • Optionally, an NCBI API key for higher rate limits

Installation Methods

Option 1: Install via Smithery (Recommended for Claude Desktop)

npx -y @smithery/cli install mcp-simple-pubmed --client claude

Option 2: Install via pip

pip install mcp-simple-pubmed

Configuration

The server requires configuration with your email address and optionally an API key:

  • PUBMED_EMAIL: Your email address (required by NCBI)
  • PUBMED_API_KEY: Optional API key for higher rate limits

Without an API key, the standard rate limit is 3 requests per second. With an API key, this increases to 10 requests per second. You can register for an API key at the NCBI website.

Setup for Claude Desktop

Add the following to your Claude Desktop configuration file (claude_desktop_config.json):

For macOS:

{
  "mcpServers": {
    "simple-pubmed": {
      "command": "python",
      "args": ["-m", "mcp_simple_pubmed"],
      "env": {
        "PUBMED_EMAIL": "your-email@example.com",
        "PUBMED_API_KEY": "your-api-key"
      }
    }
  }
}

For Windows:

{
  "mcpServers": {
    "simple-pubmed": {
      "command": "C:\\Users\\YOUR_USERNAME\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
      "args": [
        "-m",
        "mcp_simple_pubmed"
      ],
      "env": {
        "PUBMED_EMAIL": "your-email@example.com",
        "PUBMED_API_KEY": "your-api-key"
      }
    }
  }
}

Usage Notes

  • The tool returns XML-formatted full text, which provides AI assistants with additional structural information about the document.
  • If full text is not available through this tool, it may be because:
    • The article is behind a paywall
    • The article is available but not directly through PubMed
    • Access restrictions are in place
  • For articles not accessible through this tool, you may still be able to access them through:
    • A regular web browser
    • Institutional library access
    • Other research access services

Limitations

  • Cannot access paywalled or subscription-only papers
  • Depends on PubMed/NCBI API availability
  • Subject to NCBI's rate limits and terms of service

Related MCPs

Knowledge Graph Memory
Knowledge & MemoryTypeScript

A persistent memory system using a local knowledge graph

MemoryMesh
Knowledge & MemoryTypeScript

A knowledge graph server for structured memory persistence in AI models

Cognee
Knowledge & MemoryPython

Knowledge management and retrieval system with code graph capabilities

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.