Marketplace for trusted AI agent skills

Skill Detail

Search and fetch biomedical literature through MCP with PubMed MCP Server

Connect an MCP-capable agent to PubMed, Europe PMC, PMC full text, Unpaywall, citations, and MeSH tools for supervised biomedical literature workflows.

Research & ScrapingMCP
Research & Scraping MCP Security Reviewed
⭐ 153 GitHub stars ⬇ 4k/wk npm
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill search-and-fetch-biomedical-literature-through-mcp-with-pubmed-mcp-server Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
An MCP-compatible client, Node.js/npm for local stdio use or access to the hosted Streamable HTTP MCP endpoint, and network access to PubMed, Europe PMC, PMC, Unpaywall, and related biomedical literature services.
Install & setup
For local stdio use, add an MCP server entry that runs npx -y @cyanheads/pubmed-mcp-server. For hosted use, configure the MCP client for Streamable HTTP at https://pubmed.caseyjhand.com/mcp. Review the upstream README for transport, auth, and storage options before enabling it in shared workflows.
Author
cyanheads
Publisher
Organization
Last updated
Oct 4, 2026
Quick brief

Use this skill when an agent needs a bounded biomedical literature workflow instead of ad hoc web search. The operator connects PubMed MCP Server to an MCP client over stdio or Streamable HTTP, then has the agent search PubMed or Europe PMC, fetch metadata and full text where available, resolve identifiers or partial citations, format references, and ground research questions in MeSH vocabulary.

How it works

What this skill actually does

Invoke it for literature-review triage, citation lookup, evidence gathering, medical or life-science research notebooks, and reproducible source collection before writing or analysis. Do not use it as a generic npm package listing or a replacement for expert review; the boundary is MCP-mediated retrieval from the documented biomedical sources with user review of search terms, article selection, and generated summaries. Inputs are structured research questions, identifiers, citation fragments, search constraints, and MCP client configuration. Outputs should be article metadata, links, retrieved text, citations, and a transparent trail of the tools called.