Advertise
MCP.so
Sign In

PubMed MCP Server

@codingaslu

Repository

Basic information

Category

Data & Analytics

Transports

stdio

Author

codingaslu

About PubMed MCP Server

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

PubMed MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pubmed-mcp-server-codingaslu": {
      "command": "uv",
      "args": [
        "run",
        "main.py"
      ]
    }
  }
}

PubMed MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is PubMed MCP Server?

The PubMed MCP Server is a Model Context Protocol (MCP) server that searches PubMed for article abstracts using BioPython's Entrez module and the FastMCP framework. It provides asynchronous search capabilities for researchers and developers who need to retrieve PubMed data through MCP‑compatible clients.

How to use PubMed MCP Server?

Clone the repository, install dependencies with uv add -r requirements.txt, set a valid email address in main.py (Entrez.email), then start the server with uv run main.py. Configure your MCP client with the path to uv and the server directory as specified in the config.json example. Use the search_pubmed tool with parameters query (default "endocarditis") and max_results (default 10).

Key features of PubMed MCP Server

  • Searches PubMed for articles by query term.
  • Retrieves abstracts of returned articles.
  • Asynchronous execution via asyncio.to_thread.
  • Built on the FastMCP framework.
  • Configurable maximum number of results.
  • Simple Python‑based setup with uv.

Use cases of PubMed MCP Server

  • Automating literature reviews by programmatically fetching PubMed abstracts.
  • Integrating PubMed search results into AI‑powered research assistants.
  • Building MCP‑enabled tools that require live biomedical literature data.
  • Batch‑retrieving abstracts for multiple search queries in parallel.

Frequently asked questions

1

What does the PubMed MCP Server do?

It allows MCP‑compatible clients to search PubMed and retrieve article abstracts asynchronously using a single tool (`search_pubmed`).

2

What are the required dependencies?

Python 3.8 or higher, the `mcp[cli]` package, and BioPython. Dependencies are managed via `uv` and a `requirements.txt` file.

3

How do I configure the Entrez email?

You must set a valid email address in `main.py` by assigning it to `Entrez.email`. This is required by NCBI’s Entrez usage policy.

4

What are the default search parameters?

The search tool uses a default query of `"endocarditis"` and a default `max_results` of 10. Both can be overridden when calling the tool.

5

Does the server have any data storage or authentication?

No. The server does not store data locally; it queries PubMed’s public API. No authentication is required beyond the valid email address.

Comments

More Data & Analytics MCP servers

Subtext

Subtext by Fullstory

Session replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can

9

LeadBoxer

Company and contact enrichment: identify the company behind an IP, get firmographics for a domain, and profile a work email.

A

AffiliateSpy

Savassi Limited

Find the TikTok, YouTube and Instagram creators and the blogs, review sites and roundups already promoting your competitors, with the proof, then recruit them. 32 tools: competitor rosters, graded creators, roundup place

Elaichi

Elaichi is a governed remote MCP server for companies. Connect the apps your teams already run — 400+ connectors — and point Claude, ChatGPT, Cursor, any MCP client or the Elaichi Agent at one org-wide endpoint over OAut

Octolens

Octolens

Give your AI agents every brand mention across the internet — 15+ platforms, AI-filtered, one structured feed.

Advertise