europepmc-mcp-server
Enables searching and retrieving biomedical literature from Europe PMC, including abstracts, full-text (JATS XML), text-mined annotations, citations, references, and database cross-links, through natural language queries and automated data staging.
README
Europe PMC MCP Server
A Model Context Protocol (MCP) server for Europe PMC — open-access biomedical literature: search across 45M+ abstracts, retrieve OA full-text (JATS XML), text-mined annotations, citations/references, and database cross-links. One of 100+ servers in the Bio MCP monorepo.
Connect
https://europepmc-mcp-server.quentincody.workers.dev/mcp
Local dev runs at http://localhost:8904/mcp (./scripts/dev-servers.sh europepmc).
Tools
europepmc_search— discover endpoints (Code Mode catalog search)europepmc_execute— Code Mode:api.get(...)in a V8 isolate across two upstreams (Articles + Annotations APIs)europepmc_query_data— SQL over large responses auto-staged into per-session SQLiteeuropepmc_get_schema— inspect a staged dataset's schema
Wraps two upstream bases in one isolate (routed in api-adapter.ts): the Articles RESTful API (/search, /{PMCID}/fullTextXML, /{source}/{id}/citations|references|databaseLinks) and the Annotations API (/annotations/annotationsByArticleIds|annotationsByEntity). Every _execute result carries a _meta.citation (Europe PMC / EMBL-EBI).
Key usage notes (also in the catalog notes): pagination is cursorMark (start *, thread nextCursorMark; the page param is ignored); format=json is injected automatically; full text is XML-only and auto-staged; metadata/abstracts are open + commercial-OK, but per-article full-text licenses are mixed (CC-BY vs CC-BY-NC/-ND) — gate any caching/redistribution on the per-article license field (present in resultType=core).
Architecture / maintenance
- Archetype: catalog-only REST + Code Mode (dual upstream). No auth. Rate limit ~10 req/s per IP, shared across Cloudflare egress → be gentle.
- Drift risk: low. Refresh cadence: quarterly catalog review. Known gaps:
supplementaryFiles(binary ZIP) not exposed in v1; standalonetextMinedTerms/fullTextUrlListare 404 upstream (use the Annotations API / thecoreresult's inline fields).
Development
./scripts/dev-servers.sh europepmc
pnpm --filter europepmc-mcp-server run deploy
See docs/adding-mcp-servers.md and the build plan docs/plans/2026-06-26-evidence-genomics-mcp-servers.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.