Happy slice of mcp pizzaMCP.pizza

pubmed-search-mcp-server

MCP.Pizza Chef: gradusnikov

The pubmed-search-mcp-server is a Model Content Protocol server that enables searching and retrieving detailed academic paper information from the PubMed database. It supports keyword and author-based searches and provides comprehensive metadata including titles, authors, abstracts, journals, and DOIs. This server integrates seamlessly with MCP clients to facilitate real-time access to scholarly articles for research and academic workflows.

Use This MCP server To

Search PubMed articles by keywords in title or abstract Retrieve detailed metadata of academic papers including authors and DOI Integrate PubMed search results into research assistant workflows Enable real-time academic paper lookup within MCP-enabled applications Automate literature review by fetching relevant PubMed articles Support citation extraction and management from PubMed data

README

PubMedSearch MCP Server

smithery badge

A Model Content Protocol server that provides tools to search and retrieve academic papers from PubMed database.

Features

  • Search PubMed by keywords in title/abstract or author names
  • Retrieve detailed information including title, authors, journal, abstract, DOI and more

Installing via Smithery

To install pubmed-search-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gradusnikov/pubmed-search-mcp-server --client claude

Installing Manually

  1. Clone this repository:

    git clone <repository-url>
cd pubmed-search-mcp-server

  2. Install dependencies:

    pip install fastmcp requests python-dotenv

  3. Create a .env file in the project root (if needed for configuration)

Usage

  1. Start the server in development mode:

    mcp dev pubmed_search_mcp_server.py

  2. or add the server to Claude Desktop app CLAUDE_DIRECTORY/claude_desktop_config.json. For example if you are using Windows Subsystem for Linux (WSL) it may look like this:

    "pubmed-search": {
            "command": "wsl.exe",
            "args": [
                "bash",
                "-c",
                "source /home/[user]/anaconda3/etc/profile.d/conda.sh && conda activate mcp && mcp run /home/[user]/pubmed-search-mpc-server/pubmed_search_mcp_server.py"
            ]
        },

pubmed-search-mcp-server FAQ

How do I install the pubmed-search-mcp-server?
You can install it automatically via Smithery CLI or manually by cloning the repo and installing dependencies.
What information can I retrieve about a PubMed paper?
You can get the title, authors, journal, abstract, DOI, and more detailed metadata.
Can I search PubMed by author names?
Yes, the server supports searching by author names as well as keywords in titles and abstracts.
Is this server compatible with multiple MCP clients?
Yes, it is designed to integrate with various MCP clients like Claude Desktop via Smithery.
What dependencies are required to run this server?
It requires Python packages including fastmcp, requests, and python-dotenv.
How does this server handle real-time queries?
It processes search requests and returns structured PubMed data in real time for MCP clients.
Can I use this server to automate literature reviews?
Yes, it can be integrated into workflows to fetch and summarize relevant academic papers automatically.
Does it support secure and scoped access to PubMed data?
Yes, it follows MCP principles for secure, scoped, and observable model interactions.