What is Pubmed Mcp Smithery

pubmed-mcp-smithery is a Model Content Protocol server designed to enhance the search and retrieval of academic papers from the PubMed database, offering additional functionalities like MeSH term lookup, publication count statistics, and PICO-based evidence search.

Use cases

Use cases include conducting systematic reviews, comparing prevalence of medical conditions, retrieving detailed information on specific studies, and facilitating evidence-based practice in clinical settings.

How to use

To use pubmed-mcp-smithery, clone the repository from GitHub, install the necessary dependencies using pip, and run the server locally. You can also configure it to work with Claude Desktop by editing the configuration file.

Key features

Key features include keyword search with optional journal filtering, sorting results by relevance or date, retrieving related MeSH terms, getting publication counts for multiple search terms, and performing structured PICO-based searches with support for synonyms.

Where to use

pubmed-mcp-smithery can be used in academic research, healthcare, and any field that requires access to biomedical literature and enhanced search capabilities for PubMed articles.

PubMed Enhanced Search MCP Server

A Model Content Protocol server that provides enhanced tools to search and retrieve academic papers from PubMed database, with additional features such as MeSH term lookup, publication count statistics, and PICO-based evidence search.

Features

• Search PubMed by keywords with optional journal filter
• Support for sorting results by relevance or date (newest/oldest first)
• Get MeSH (Medical Subject Headings) terms related to a search word
• Get publication counts for multiple search terms (useful for comparing prevalence)
• Retrieve detailed paper information including abstract, DOI, authors, and keywords
• Perform structured PICO-based searches with support for synonyms and combination queries

Installing

Prerequisites

• Python 3.6+
• pip

Installation

1. Clone this repository:

   git clone https://github.com/leescot/pubmed-mcp-smithery
   cd pubmed-mcp-smithery
   

2. Install dependencies:

   pip install fastmcp requests
   

Usage

Running locally

Start the server:

python pubmed_enhanced_mcp_server.py

For development mode with auto-reloading:

mcp dev pubmed_enhanced_mcp_server.py

Adding to Claude Desktop

Edit your Claude Desktop configuration file (CLAUDE_DIRECTORY/claude_desktop_config.json) to add the server:

MCP Functions

The server provides these main functions:

1. search_pubmed - Search PubMed for articles matching keywords with optional journal filtering

   # Example
   results = await search_pubmed(
       keywords=["diabetes", "insulin resistance"],
       journal="Nature Medicine",
       num_results=5,
       sort_by="date_desc"
   )
   

2. get_mesh_terms - Look up MeSH terms related to a medical concept

   # Example
   mesh_terms = await get_mesh_terms("diabetes")
   

3. get_pubmed_count - Get the count of publications for multiple search terms

   # Example
   counts = await get_pubmed_count(["diabetes", "obesity", "hypertension"])
   

4. format_paper_details - Get detailed information about specific papers by PMID

   # Example
   paper_details = await format_paper_details(["12345678", "87654321"])
   

5. pico_search - Perform structured PICO (Population, Intervention, Comparison, Outcome) searches with synonyms

   # Example
   pico_results = await pico_search(
       p_terms=["diabetes", "type 2 diabetes", "T2DM"],
       i_terms=["metformin", "glucophage"],
       c_terms=["sulfonylurea", "glipizide"],
       o_terms=["HbA1c reduction", "glycemic control"]
   )
   

PICO Search Functionality

The PICO search tool helps researchers conduct evidence-based literature searches by:

1. Allowing multiple synonym terms for each PICO element
2. Combining terms within each element using OR operators
3. Performing AND combinations between elements (P AND I, P AND I AND C, etc.)
4. Returning both search queries and publication counts for each combination

This approach helps refine research questions and identify the most relevant literature.

Rate Limiting

The server implements automatic retry mechanism with backoff delays to handle potential rate limiting by NCBI’s E-utilities service.

License

This project is licensed under the BSD 3-Clause License - see the LICENSE file for details.