Mcp Simple Pubmed

Overview

What is MCP Simple PubMed?

MCP Simple PubMed is a powerful server designed for searching and querying the PubMed medical papers and research database. It provides users with an efficient way to access a vast repository of medical literature, making it easier for researchers, healthcare professionals, and students to find relevant studies and articles.

Features of MCP Simple PubMed

User-Friendly Interface: The platform is designed with simplicity in mind, allowing users to navigate easily and find the information they need without any hassle.
Comprehensive Search Capabilities: Users can perform detailed searches using various filters to narrow down results based on specific criteria such as publication date, author, and keywords.
Access to Full Texts: MCP Simple PubMed often provides links to full-text articles, enabling users to access the complete research papers directly from the search results.
Regular Updates: The database is frequently updated to include the latest research findings, ensuring that users have access to the most current information available.
Open Access: As a public repository, MCP Simple PubMed allows anyone to search and access its resources without any subscription fees.

How to Use MCP Simple PubMed

Visit the Website: Go to the MCP Simple PubMed website to access the search interface.
Enter Search Terms: Input relevant keywords, phrases, or author names into the search bar to begin your query.
Apply Filters: Utilize the available filters to refine your search results based on publication date, article type, or other criteria.
Review Results: Browse through the list of articles that match your search criteria. Click on titles to view abstracts or full texts where available.
Save or Share: You can save your search results or share them with colleagues for further discussion or collaboration.

Frequently Asked Questions

Q: Is MCP Simple PubMed free to use?

A: Yes, MCP Simple PubMed is a public resource and is free to access for all users.

Q: How often is the database updated?

A: The database is updated regularly to include the latest research articles and publications.

Q: Can I access full-text articles through MCP Simple PubMed?

A: Yes, many articles provide links to their full texts, allowing users to read the complete studies.

Q: What types of articles can I find in MCP Simple PubMed?

A: You can find a wide range of articles, including clinical studies, reviews, meta-analyses, and case reports across various medical fields.

Q: How can I contact support for MCP Simple PubMed?

A: For support or inquiries, you can typically find contact information on the website or through the help section.

Details

An MCP server that provides access to PubMed articles through the Entrez API.

Features

Search PubMed database using keywords
Access article abstracts
Download full text when available (for open access articles available directly on PubMed)

Please note that the tool returns XML-ized version of full text. It is however more useful for AIs than a "human readable" text would have been as it gives them additional information about document's structure. At least, this is what Claude 3.5 Sonnet said he prefers.

Please also note that inability of this tool and possibly other tools to deliver a paper's full text may not be due to the fact that it is not available. When testing this tool I came across a paper that did not have full text on PubMed and when Claude accessed the publication URL (which we did get through DOI) using fetch he did get a "forbidden” error. However, I was able to access the very same page using a regular browser.

In other words if your AI assistant is not able to get the full text of a paper using this tool it is worth trying manually with a regular web browser.

Finally, this tool of course can’t give you access to paywalled/paid papers. You may be able to read them through your library access or – as a last resort – through a certain site that strives to make publicly funded research freely available.

Installation

Installing via Smithery

To install Simple PubMed for Claude Desktop automatically via Smithery:

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

Manual Installation

pip install mcp-simple-pubmed

Configuration

The server requires the following environment variables:

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

The standard rate limit is 3 requests / second. No rate limiting was implemented, as it is highly unlikely in the typical usage scenario that your AI would generate more traffic. If you need it, you can register for an API key which will give you 10 requests / second. Read about this on NCBI pages.

Usage with Claude Desktop

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

(Mac OS)

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

(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" 
      }
    }
  }
}

macOS SSL Certificate Fix

If you encounter SSL certificate verification errors on macOS (such as [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain), you need to install the proper certificate bundle:

/Applications/Python\ 3.13/Install\ Certificates.command

Replace 3.13 with your Python version number. This script comes with Python installations from python.org.

You can also run it from the Finder:

If you perform this change while Claude Desktop is open you will need to quit it and start it again for it to take effect.

License

MIT License

{ "mcpServers": { "mcp-simple-pubmed": { "command": "docker", "args": [ "run", "-i", "--rm", "ghcr.io/metorial/mcp-container--andybrandt--mcp-simple-pubmed--mcp-simple-pubmed", "mcp-simple-pubmed" ], "env": { "PUBMED_EMAIL": "pubmed-email", "PUBMED_API_KEY": "pubmed-api-key" } } } }