search_pubmed
Search PubMed for medical and life sciences research articles.
LABSCO SUMMARY
The prompts are the part that changes the results.
Anyone can hand a model a search endpoint; what you get back is a naive keyword query. The systematic-review and PICO prompts push it to build the query a librarian would — MeSH terms, synonyms, date filters, a structured clinical question — which is the difference between a plausible reading list and a defensible one. Full text arrives as XML on purpose, so the model can tell a methods section from a discussion.
What it is
An MCP server over PubMed through NCBI's Entrez API, with three parts: search tools, abstract and metadata access via resource URIs, and prompts that help build a good query rather than a naive one.
What you get
- Search across the database using keywords, MeSH terms, author names, date ranges and Boolean operators
- Full text downloaded where it is available — for open access articles in PubMed Central — returned as XML rather than flattened prose, because the document structure is useful to a model
- Article abstracts and metadata retrieved through resource URIs
- Prompts that construct the query for you: a systematic review search with MeSH terms, synonyms and date filters; a PICO-framework clinical question; and a properly formatted author search
- Straight talk about the limits — the README says a failed full-text fetch does not mean the text is unavailable, and that paywalled papers are out of reach
Requirements
Python, and pip install mcp-simple-pubmed (0.1.16), or a Smithery one-liner for Claude Desktop. PUBMED_EMAIL is required — NCBI asks for a contact address. PUBMED_API_KEY is optional and raises the rate limit from 3 requests per second to 10; the server implements no rate limiting of its own on the grounds that typical assistant use will not approach the cap. On macOS an SSL certificate verification failure is fixed by running the Certificates.command script that ships with a python.org install, then restarting the client. Licensed MIT.
Setup effort
One command plus credentials — pip install mcp-simple-pubmed, then supply credentials
USE CASES
01
Building a systematic review search strategy
Use the systematic review prompt to generate the MeSH terms, synonyms and date filters, then run it and refine.
02
Turning a clinical question into a searchable one
Work through the PICO prompt so population, intervention, comparison and outcome each become search terms.
03
Reading a paper's methods, not just its abstract
Fetch the full text for open-access articles; the XML keeps the section structure intact for the model.
04
Finding everything by one author
Use the author search prompt, which handles the name formatting PubMed expects.
2 tools
Listed in project code.
get_paper_fulltext
Get full text of a PubMed article using its ID.
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools registered in the project's code.
Requires
- python on PATH
- PUBMED_EMAIL in your environment
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install mcp-simple-pubmedMCP Clients
Claude Desktop — macOS
CLAUDE DESKTOP — MACOS · JSON
{
"mcpServers": {
"simple-pubmed": {
"command": "python",
"args": [
"-m",
"mcp_simple_pubmed"
],
"env": {
"PUBMED_EMAIL": "<YOUR_PUBMED_EMAIL>",
"PUBMED_API_KEY": "<YOUR_PUBMED_API_KEY>"
}
}
}
}Claude Desktop — Windows
CLAUDE DESKTOP — WINDOWS · JSON
{
"mcpServers": {
"simple-pubmed": {
"command": "C:\\Users\\<YOUR_USERNAME>\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
"args": [
"-m",
"mcp_simple_pubmed"
],
"env": {
"PUBMED_EMAIL": "<YOUR_PUBMED_EMAIL>",
"PUBMED_API_KEY": "<YOUR_PUBMED_API_KEY>"
}
}
}
}
