# PyEuropePMC

> PyEuropePMC is an open-source MCP server for health and science. Europe PMC literature search, full text and export for AI agents (Python, MIT). It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, self-hosted
- **Website:** https://jonasheinickebio.github.io/pyEuropePMC/
- **Repository:** https://github.com/jonasheinickebio/pyeuropepmc
- **MCP Registry name:** io.github.JonasHeinickeBio/pyeuropepmc
- **Categories:** health and science, web search and scraping
- **Listing updated:** 2026-11-14

## About

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.

## Features

- **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

## Install

### Claude Code (Terminal)

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

### Claude Desktop (claude_desktop_config.json)

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

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

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

## 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

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Tooluniverse](https://ai-powered.com/mcp/tooluniverse): Tooluniverse is an open-source MCP server for health and science.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Oya Browser](https://ai-powered.com/mcp/oya-browser): Oya Browser is a freemium MCP server for browser automation.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Later Stages](https://ai-powered.com/mcp/later-stages): Later Stages is a free MCP server for health and science.

---
Source: https://ai-powered.com/mcp/pyeuropepmc
