home / mcp / pubmed mcp server
MCP server for searching and querying PubMed medical papers/research database
Configuration
View docs{
"mcpServers": {
"andybrandt-mcp-simple-pubmed": {
"command": "python",
"args": [
"-m",
"mcp_simple_pubmed"
],
"env": {
"PUBMED_EMAIL": "[email protected]",
"PUBMED_API_KEY": "your-api-key"
}
}
}
}You can access PubMed articles through an MCP server that exposes PubMed data via the Entrez API. This server lets you search PubMed, retrieve abstracts, and download full text when available for open access articles. It also includes prompts to help you construct effective PubMed queries for systematic reviews, PICO questions, and author searches.
Connect to the MCP server from your MCP client and use the provided tools to search PubMed, fetch abstracts, and download open access full text when available. You can also leverage the built-in prompts to generate optimized PubMed queries for common literature search scenarios.
Prerequisites you need before installing: - Python 3.x installed on your system - An active internet connection for package install and PubMed API access Install via the manual method: 1. Open a terminal or command prompt 2. Run the installation command below to install the MCP package from PyPI.
pip install mcp-simple-pubmedIf you prefer to install automatically for Claude Desktop using Smithery, run the following command.
npx -y @smithery/cli install mcp-simple-pubmed --client claudeSearch the PubMed database using keywords, MeSH terms, author names, date ranges, and Boolean operators.
Download full text when available for open access PubMed Central articles.
Retrieve article abstracts and metadata via resource URIs.