Pubmed MCP Smithery

🚀 Enhanced PubMed Search MCP Server

An Model Content Protocol (MCP) server that provides enhanced tools for searching and retrieving academic papers from the PubMed database. It comes with additional features such as MeSH term lookup, publication count statistics, and PICO-based evidence search.

🚀 Quick Start

This server offers enhanced tools for searching and retrieving academic papers from the PubMed database, with additional features like MeSH term lookup, publication count statistics, and PICO-based evidence search.

✨ Features

• Search PubMed by keywords with optional journal filtering.
• Support sorting results by relevance or date (newest/oldest first).
• Retrieve MeSH (Medical Subject Headings) terms related to search terms.
• Get the publication count for multiple search terms (for popularity comparison).
• Retrieve detailed paper information, including abstracts, DOIs, authors, and keywords.
• Support PICO (Population, Intervention, Comparison, Outcome) structured search, with support for synonyms and combined queries.

📦 Installation

Prerequisites

• Python 3.6+
• pip

Installation Steps

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 Examples

Basic Usage

Local Run

Start the server:

python pubmed_enhanced_mcp_server.py

Run in development mode (auto-reload):

mcp dev pubmed_enhanced_mcp_server.py

Add to Claude Desktop

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

"pubmed-enhanced": {
    "command": "python",
    "args": [
        "/path/pubmed-mcp-smithery(pubmed_enhanced_mcp_server.py"
    ]
}

Advanced Usage

The server provides the following main functions:

search_pubmed

Search PubMed articles based on keywords with optional journal filtering.

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

get_mesh_terms

Find MeSH terms related to medical concepts.

# Example
mesh_terms = await get_mesh_terms("Diabetes")

get_pubmed_count

Get the publication count for multiple search terms.

# Example
counts = await get_pubmed_count(["Diabetes", "Obesity", "Hypertension"])

format_paper_details

Retrieve detailed information about specific papers based on PMIDs.

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

pico_search

Perform a structured search based on PICO (Population, Intervention, Comparison, Outcome), supporting synonyms and combined queries.

# Example
pico_results = await pico_search(
    p_terms=["Diabetic patients", "Non-diabetic patients"],
    i_terms=["Metformin"],
    c_terms=["Placebo"],
    o_terms=["Blood glucose level"]
)

📚 Documentation

⚠️ Important Note

Adjust the parameters in the code examples according to your actual needs.

💡 Usage Tip

The PICO search function supports complex medical queries. You can perform advanced filtering by specifying the population (p_terms), intervention (i_terms), comparison (c_terms), and outcome (o_terms).

📄 License

This software is licensed under [License Name]. Please refer to the project repository for the specific content.