Skip to content
MCP server

PyEuropePMC

Europe PMC literature search, full text and export for AI agents (Python, MIT)

Runs locallyStatus and history
Pricing
Open source
Platforms
CLI, self-hosted
Runs
Locally
Version
4.8.0
Listing updated
3 days ago

About PyEuropePMC

PyEuropePMC is an open-source MCP server for health and science. It runs locally on your machine and is started by your AI client.

The server ships inside the pyeuropepmc Python package, installed from PyPI and run over stdio with the pyeuropepmc-mcp command. Its registry entry lists areas such as search analytics, enrichment, PICO, MeSH, data links and export, so an agent can go from a query to structured output without custom glue code.

Under the hood is a client for Europe PMC that can also query ten other sources in one search, including PubMed, arXiv, ClinicalTrials.gov, OpenAlex, Semantic Scholar, CORE, DBLP, DOAJ, HAL and Zenodo, merging duplicates. Open-access papers can be fetched as JATS XML, PDF or HTML, and the XML parser returns metadata, tables, figures, references and typed sections suited to retrieval-augmented generation.

Optional environment variables switch on extras: a Semantic Scholar key raises rate limits, an Unpaywall email enables open-access lookups, and an OpenAI-compatible key turns on LLM-driven tools such as literature_review and paper_screening. PDFs are saved to a folder you choose on the machine running the server.

Install

Run in a terminal

claude mcp add pyeuropepmc --env SEMANTIC_SCHOLAR_API_KEY='<SEMANTIC_SCHOLAR_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- uvx pyeuropepmc

Add to claude_desktop_config.json

{
  "mcpServers": {
    "pyeuropepmc": {
      "command": "uvx",
      "args": [
        "pyeuropepmc"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "<SEMANTIC_SCHOLAR_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "pyeuropepmc": {
      "command": "uvx",
      "args": [
        "pyeuropepmc"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "<SEMANTIC_SCHOLAR_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "pyeuropepmc": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pyeuropepmc"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "<SEMANTIC_SCHOLAR_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pyeuropepmc": {
      "command": "uvx",
      "args": [
        "pyeuropepmc"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "<SEMANTIC_SCHOLAR_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "pyeuropepmc": {
      "command": "uvx",
      "args": [
        "pyeuropepmc"
      ],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "<SEMANTIC_SCHOLAR_API_KEY>",
        "OPENAI_API_KEY": "<OPENAI_API_KEY>"
      }
    }
  }
}

Configuration

  • PYEUROPEPMC_MCP_LOG_LEVELLog level, written to stderr: DEBUG, INFO, WARNING or ERROR.
  • SEMANTIC_SCHOLAR_API_KEYOptional. Raises the Semantic Scholar rate limit used by citation_snowball, the semantic_scholar source of unified_search and the DOI route of download_papers_pdf; without it requests are throttled and may get HTTP 429.
  • OPENAI_API_KEYOptional. Enables the LLM-powered tools (analyze_citations, literature_review, paper_screening, ...) with any OpenAI-compatible API. Needs the agentic extra.
  • OPENAI_BASE_URLOptional. Base URL of an OpenAI-compatible API for the LLM tools.
  • OPENAI_MODELOptional. Model for the LLM tools.
  • UNPAYWALL_EMAILOptional. Your contact e-mail address, sent with each Unpaywall request (their terms ask for one). Used by the find_open_access and download_papers_pdf tools (without it download_papers_pdf skips the Unpaywall source); there is no default.
  • PYEUROPEPMC_MCP_DOWNLOAD_DIROptional. Folder where the download_papers_pdf tool saves PDFs on the machine running the server. Default: ~/Downloads/pyeuropepmc.

What it does

Multi-source search
Queries Europe PMC and ten other scholarly sources at once and merges duplicate records.
Full-text retrieval
Downloads open-access papers as XML, PDF or HTML, with the source and licence of each PDF.
JATS parsing
Extracts metadata, authors, tables, figures, references and typed sections from article XML.
Citation and enrichment
Walks citation graphs and adds metadata from Crossref, OpenAlex, Unpaywall, DataCite, ORCID and others.
Systematic-review logs
Records each query, its filters and result count in PRISMA-style search logs.
Optional LLM tools
With an OpenAI-compatible key, adds tools for literature review and paper screening.

Good for

  • Search biomedical literature from an AI assistant and pull the open-access full text
  • Build a retrieval corpus of parsed paper sections for RAG
  • Keep an auditable search log for a systematic review
  • Snowball through citations from a seed paper
  • Export parsed articles as RDF for a knowledge graph

Pricing

Open source

Free, MIT licensed; optional third-party API keys are your own

Prices change. Check jonasheinickebio.github.io before you buy.

PyEuropePMC FAQ

Which Python versions does it support?

The project site lists Python 3.10 to 3.13.

Is an API key required?

No. The Semantic Scholar, OpenAI-compatible and Unpaywall settings are all optional and only unlock extra features or higher rate limits.

Where do downloaded PDFs go?

To ~/Downloads/pyeuropepmc by default, or the folder set in PYEUROPEPMC_MCP_DOWNLOAD_DIR on the machine running the server.

What licence is it under?

MIT.

Is PyEuropePMC free?

Yes. PyEuropePMC is open source, so you can use and self-host it for free.

How do I add PyEuropePMC to Claude Code?

Run this command in your terminal: claude mcp add pyeuropepmc --env SEMANTIC_SCHOLAR_API_KEY='<SEMANTIC_SCHOLAR_API_KEY>' --env OPENAI_API_KEY='<OPENAI_API_KEY>' -- uvx pyeuropepmc

What are the best alternatives to PyEuropePMC?

The closest alternatives to PyEuropePMC are Scrapling MCP Server, Firecrawl MCP Server, Tooluniverse, SearXNG Search and Oya Browser.

Alternatives to PyEuropePMC

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. Tooluniverse

    MCP server

    MCP server giving AI agents access to thousands of scientific research tools

    Runs locally
    • Open source
    • 1.8K GitHub stars
    • Health and science
  4. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  5. Oya Browser

    MCP server

    HIPAA-oriented agentic browser with replayable playbooks, reachable over MCP

    • 32 tools
    • Remote
    • Freemium
    • 349 GitHub stars
    • Browser automation
  6. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping