How do I install PyEuropePMC?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does PyEuropePMC need an API key?

The publisher lists these environment variables: PYEUROPEPMC_MCP_LOG_LEVEL, SEMANTIC_SCHOLAR_API_KEY, OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL, UNPAYWALL_EMAIL, PYEUROPEPMC_MCP_DOWNLOAD_DIR.

What transport does PyEuropePMC use?

PyEuropePMC runs locally over stdio.

When was PyEuropePMC last checked?

Last checked 2026-11-11. Europe PMC search, search analytics, full text, enrichment, PICO, MeSH, data links, export, auth

PyEuropePMC MCP server

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

uvx pyeuropepmc==4.8.0

Credentials from the publisher

PYEUROPEPMC_MCP_LOG_LEVEL — Log level, written to stderr: DEBUG, INFO, WARNING or ERROR.
SEMANTIC_SCHOLAR_API_KEY — Optional. 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_KEY — Optional. Enables the LLM-powered tools (analyze_citations, literature_review, paper_screening, ...) with any OpenAI-compatible API. Needs the agentic extra.
OPENAI_BASE_URL — Optional. Base URL of an OpenAI-compatible API for the LLM tools.
OPENAI_MODEL — Optional. Model for the LLM tools.
UNPAYWALL_EMAIL — Optional. 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_DIR — Optional. Folder where the download_papers_pdf tool saves PDFs on the machine running the server. Default: ~/Downloads/pyeuropepmc.

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1PYEUROPEPMC_MCP_LOG_LEVEL=<value> SEMANTIC_SCHOLAR_API_KEY=<secret> OPENAI_API_KEY=<secret> OPENAI_BASE_URL=<value> OPENAI_MODEL=<value> UNPAYWALL_EMAIL=<value> PYEUROPEPMC_MCP_DOWNLOAD_DIR=<value> claude mcp add io.github.jonasheinickebio-pyeuropepmc -- uvx pyeuropepmc==4.8.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "io.github.jonasheinickebio-pyeuropepmc": {4      "command": "uvx",5      "args": [6        "pyeuropepmc==4.8.0"7      ],8      "env": {9        "PYEUROPEPMC_MCP_LOG_LEVEL": "<value>",10        "SEMANTIC_SCHOLAR_API_KEY": "<secret>",11        "OPENAI_API_KEY": "<secret>",12        "OPENAI_BASE_URL": "<value>",13        "OPENAI_MODEL": "<value>",14        "UNPAYWALL_EMAIL": "<value>",15        "PYEUROPEPMC_MCP_DOWNLOAD_DIR": "<value>"16      }17    }18  }19}

claude_desktop_config.json

Local · pypiPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

PyEuropePMC

PyEuropePMC is a Python client for Europe PMC. It searches the literature, downloads open-access full text, and parses JATS XML into metadata, plain text and structured sections. It also ships a command-line tool and an MCP server for AI agents.

✨ Features

Europe PMC search with plain queries or a fluent QueryBuilder, pagination, and results as JSON, XML or Dublin Core. Search guide
Ten more sources in one search, with duplicates merged: PubMed, arXiv, ClinicalTrials.gov, OpenAlex, Semantic Scholar, CORE, DBLP, DOAJ, HAL and Zenodo. Semantic Scholar needs the semanticscholar extra and CORE an API key. Multi-source search
Full text: XML (Europe PMC first, then other open sources), PDF and HTML, plus bulk PDF downloads from the Europe PMC FTP site. Full-text retrieval
JATS XML parsing: metadata, authors, tables, figures and references; plain text and Markdown; typed sections for retrieval-augmented generation (RAG); JATS normalization and BioC export. XML parsing, JATS normalization
Text-mining annotations for genes, diseases, chemicals and their relationships. Examples
Citations and metadata: walk citation graphs, and enrich records from Crossref, Unpaywall, OpenAlex, Semantic Scholar, DataCite, ORCID, ROR and iCite. Citation walking, Enrichment
Analysis: pandas DataFrames, citation statistics, duplicate detection, plots, and PRISMA-style search logs for systematic reviews. Analytics, Review tracking
RDF knowledge graphs from parsed articles, mapped by the that ships with the package; pass or to use your own.

📦 Installation

pip install pyeuropepmc                              # core
pip install "pyeuropepmc[analytics,visualization]"   # add extras (quote the brackets)
pip install "pyeuropepmc[all]"                       # every optional feature

PyEuropePMC supports Python 3.10 to 3.13. The core install covers search, full-text download, XML parsing, RDF, the command line and the MCP server. The extras add:

Extra	Installs	Adds
`analytics`	pandas, numpy	`to_dataframe`, `citation_statistics`, `quality_metrics`, `remove_duplicates` and CSV export
`visualization`	matplotlib, seaborn, pandas, numpy	The `plot_*` functions and `create_summary_dashboard`
`export`	pandas, tabulate, xlsxwriter	Excel and Markdown-table export (`pyeuropepmc.utils.export`)
`semanticscholar`	semanticscholar	`SemanticScholarClient` and the `semantic_scholar` search source
`enrichment`	semanticscholar	Semantic Scholar data in `PaperEnricher`
`bibliography`	bibtexparser	BibTeX parsing, validation and RIS/CSL conversion, including the `bib_*` MCP tools
`zotero`	pyzotero	The Zotero client
`agentic`	openai, langchain, langchain-openai, langgraph, jinja2	LLM analysis, the LLM MCP tools and `pyeuropepmc claim`
`ui`	flask, tornado	The web UI (`pyeuropepmc claim serve`)
`signing`	cryptography	Signed search logs for systematic reviews
`benchmark`	huggingface-hub	Downloading the published benchmark datasets (`pyeuropepmc benchmark download`)
`rdf`	nothing	Kept so existing installs keep working; the core rdflib writes JSON-LD itself
`standard`	jupyterlab, notebook, ipykernel, ipython, ipywidgets, matplotlib, seaborn, pandas, numpy, tabulate, xlsxwriter, requests-cache, rich	Jupyter plus the analytics, plotting and export packages
`all`	all of the above

Upgrading from 1.x? The migration guide lists what moved into extras.

🚀 Quick start

from pyeuropepmc import FullTextClient, FullTextXMLParser, QueryBuilder, SearchClient

# 1. Search Europe PMC for open-access articles ("CRISPR AND OPEN_ACCESS:y")
query = QueryBuilder().keyword("CRISPR").and_().field("open_access", True).build()
with SearchClient() as search:
    hits = search.search_and_parse(query, pageSize=10)
pmcid = next(hit["pmcid"] for hit in hits if hit.get("pmcid"))

# 2. Download the article's JATS XML (raises an error if no source has it)
with FullTextClient() as fulltext:
    xml_path = fulltext.download_xml_by_pmcid(pmcid, output_path=f"articles/{pmcid}.xml")

# 3. Parse it
parser = FullTextXMLParser(xml_path.read_text(encoding="utf-8"))
metadata = parser.extract_metadata()
print(metadata["title"])
print(", ".join(metadata["authors"][:3]))
text = parser.to_plaintext()  # or parser.to_markdown()

# 4. Collect text blocks with their section path, ready to chunk and embed for RAG
chunks = []
for section in parser.get_full_text_sections_structured():
    if section["section_type"] not in ("front", "body"):  # skip back matter and appendices
        continue
    for block in section["content"]:
        if block.get("text"):
            path = section.get("section_path", section["title"])
            chunks.append({"section": path, "type": block["type"], "text": block["text"]})
print(f"{len(chunks)} text blocks")

section_type is front for the title and abstract, then body, back or appendix. Each block has a type such as paragraph, list, table or figure. Tables and figures carry label and caption, and tables also carry rows. The XML parsing guide covers the other extractors.

🔒 Safe XML parsing

PyEuropePMC parses every XML document it reads with defusedxml: full-text articles, Europe PMC search results, arXiv and PubMed responses, and local files. A DOCTYPE declaration is accepted, but a document that declares entities, internal or external, is refused rather than expanded; FullTextXMLParser raises ParsingError. lxml is not used and does not need to be installed.

💻 Command line

Command	What it does
`pyeuropepmc unified_search`	`search` several sources with deduplication, or `compare-sources` to see each source's results
`pyeuropepmc normalize`	Turn JATS XML into clean text (`text`), sections (`sections`) or BioC JSON (`bioc`); `classify` a heading; `batch` a directory
`pyeuropepmc benchmark`	Score and profile the XML parser on a local folder or a published dataset
`pyeuropepmc claim`	Check the claims in a text against Europe PMC literature with LLM agents (needs the `agentic` extra and an API key)

pyeuropepmc unified_search search "CRISPR base editing" --limit 10 --output results.json
pyeuropepmc benchmark list-datasets

unified_search search queries Europe PMC, PubMed and arXiv unless you pass --source. Add --help to any command for its options.

🤖 MCP server

pyeuropepmc-mcp serves 42 tools over the Model Context Protocol: multi-source search with date, open-access and source filters, a query linter, builder, PubMed translator and evaluator (Europe PMC answers a malformed query with a different result instead of an error), a service-status probe and cache controls, BibTeX, RIS, CSL-JSON, CSV and Markdown export, hit counts, paper details (also for up to 100 papers at once), citations and references, open-access full text as markdown or typed sections (with a section filter and a size cap, so a long paper fits in one response), free copies of papers that are not open access in Europe PMC (via Unpaywall), text-mined entity annotations (genes, chemicals, diseases) of a paper or across papers, data and lab links of a paper (accession numbers, BioStudies, model-organism databases), citation-graph walking, ClinicalTrials.gov search, figure extraction, a local full-text index, bibliography conversion and LLM-powered analysis. The server is part of the core install. pip install "pyeuropepmc[all]" enables every tool; otherwise the bib_* tools need bibliography, and the LLM tools need agentic plus an OpenAI-compatible API key (see Configuration below).

pyeuropepmc-mcp                                # stdio, for Claude Desktop and similar clients
pyeuropepmc mcp                                # the same server, through the CLI
pyeuropepmc-mcp --transport streamable-http    # HTTP at http://127.0.0.1:8000/mcp

For Claude Desktop and other clients that start the server themselves:

{
  "mcpServers": {
    "pyeuropepmc": {
      "command": "pyeuropepmc-mcp"
    }
  }
}

Without an install, "command": "uvx" with "args": ["pyeuropepmc", "mcp"] does the same; this is what the MCP Registry entry tells clients to run. For Claude Code, one command adds it:

claude mcp add pyeuropepmc -- uvx pyeuropepmc mcp

Cursor (.cursor/mcp.json) and VS Code (.vscode/mcp.json, under "servers" instead of "mcpServers") take the same command and args.

The server has no authentication of its own, so keep the HTTP transport on 127.0.0.1 or put an authenticating proxy in front of it. The MCP server guide lists every tool. The server is listed in the MCP Registry as io.github.JonasHeinickeBio/pyeuropepmc.

⚙️ Configuration

Europe PMC needs no API key. Other services read these environment variables. A value passed in code, such as FullTextClient(email=...) or EnrichmentConfig(unpaywall_email=...), takes precedence.

Variable	Used for
`UNPAYWALL_EMAIL`, `CROSSREF_EMAIL`	Contact e-mail for Unpaywall and Crossref. `FullTextClient` needs one of them for its Unpaywall fallback, and so does the MCP tool `find_open_access`.
`OPENALEX_EMAIL`, `DATACITE_EMAIL`, `ROR_EMAIL`, `ROR_CLIENT_ID`	The other enrichment sources
`SEMANTIC_SCHOLAR_API_KEY`	Semantic Scholar, with higher rate limits
`CORE_API_KEY`	The `core` search source
`OPENAI_API_KEY`, `OPENAI_BASE_URL`, `OPENAI_MODEL`	LLM features, with any OpenAI-compatible API; the model defaults to `gpt-4o-mini`
`ZOTERO_API_KEY`, `ZOTERO_LIBRARY_ID`, `ZOTERO_LOCAL`	The Zotero client
`PYEUROPEPMC_MCP_TRANSPORT`, `PYEUROPEPMC_MCP_HOST`, `PYEUROPEPMC_MCP_PORT`, `PYEUROPEPMC_MCP_LOG_LEVEL`	Defaults for the `pyeuropepmc-mcp` options

The pyeuropepmc command also loads the first .env file it finds in the current directory, one of its parents, or ~/.config/pyeuropepmc/. Variables that are already set keep their values.

📚 Documentation

The guides are in docs/. Start with installation and the quick start, or go straight to the API reference, caching, the example scripts and the changelog.

Parser benchmark. On the 55 JATS articles in benchmark_xmls/xml, the parser's mean composite quality score is 0.998 (measured on 2026-09-15). The benchmarking guide explains the metrics. To reproduce the score from a source checkout, or to score a published dataset:

pyeuropepmc benchmark run local --local-path benchmark_xmls/xml --limit 55
pyeuropepmc benchmark download PLOS_1000   # 1,000 articles, 1.3 GB
pyeuropepmc benchmark run PLOS_1000

The weekly benchmark workflow times the API clients and opens a pull request that refreshes the section below.

📊 Performance

Last updated: 2026-09-14

Metric	Value
Benchmarked methods	10
Total requests	224
Mean call time	0.871s
Success rate	100.0%

🚀 pyEuropePMC Benchmark Suite

Generated: 2026-09-14 07:45:39

📊 Summary

Total Benchmarks: 6
Total Methods: 10
Successful Runs: 10
Failed Runs: 0
Cache Enabled: 5

ArticleClient_NoCache

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
get_article_details	1.707s	0.212s	0.0MB	❌	31	0
p50: 1.620s · p95: 2.235s · ops: 0.59/s · runs: 30
get_citations	1.789s	0.318s	0.0MB	❌	31	0
p50: 1.666s · p95: 2.851s · ops: 0.56/s · runs: 30

ArticleClient_Cached

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
get_article_details	<1ms	<1ms	0.0MB	✅	1	0
p50: 17µs · p95: 29µs · ops: 53390.19/s · runs: 30
get_citations	<1ms	<1ms	0.0MB	✅	1	0
p50: 19µs · p95: 30µs · ops: 48437.33/s · runs: 30

SearchClient_NoCache

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
search	2.074s	0.262s	0.1MB	❌	31	0
p50: 1.964s · p95: 2.673s · ops: 0.48/s · runs: 30
get_hit_count	2.085s	0.562s	0.0MB	❌	31	0
p50: 1.933s · p95: 3.668s · ops: 0.48/s · runs: 30

SearchClient_Cached

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
search	<1ms	<1ms	0.0MB	✅	1	0
p50: 109µs · p95: 134µs · ops: 8795.90/s · runs: 30
get_hit_count	<1ms	<1ms	0.0MB	✅	1	0
p50: 111µs · p95: 137µs · ops: 8603.62/s · runs: 30

FullTextClient_NoCache

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
check_fulltext_availability	1.050s	0.148s	0.1MB	❌	93	0
p50: 0.998s · p95: 1.388s · ops: 0.95/s · runs: 30

FullTextClient_Cached

Method	Mean Time	Std Dev	Mean Memory	Cache	Requests	Errors
check_fulltext_availability	<1ms	<1ms	0.0MB	✅	3	0
p50: 20µs · p95: 21µs · ops: 48496.45/s · runs: 30

🔁 Cache vs No-Cache Comparison

ArticleClient — cached vs no-cache

Method	No-Cache Mean	Cached Mean	Speedup (no/cache)
get_article_details	1.707s	<1ms	>17074.4x
get_citations	1.789s	<1ms	>17888.5x

FullTextClient — cached vs no-cache

Method	No-Cache Mean	Cached Mean	Speedup (no/cache)
check_fulltext_availability	1.050s	<1ms	>10504.7x

SearchClient — cached vs no-cache

Method	No-Cache Mean	Cached Mean	Speedup (no/cache)
get_hit_count	2.085s	<1ms	17941.89x
search	2.074s	<1ms	18245.92x

Average speedup for SearchClient (no-cache / cached): 18093.91x

Notes: Means are computed over measured iterations; '-' indicates missing data. Values like '<1ms' indicate very fast cached responses. Speedups shown as lower-bounds when cached times are too small to measure precisely.

⚙️ How to reproduce

Run the modular benchmark locally and regenerate these artifacts:

pytest tests/benchmark_article_client.py::test_modular_benchmark_system -m benchmark --force-enable-socket --timeout=3600

Detailed JSON results: MODULAR_BENCHMARK_RESULTS.json

🤝 Contributing

Contributions are welcome. The development guide covers setup, testing, code quality and the release process. Report bugs and suggest features in the issue tracker.

📝 Citation

If PyEuropePMC supports your research, please cite it and give the version you used (pip show pyeuropepmc prints it):

@software{pyeuropepmc,
  author = {Heinicke, Jonas},
  title  = {{PyEuropePMC}: a Python toolkit for Europe PMC},
  url    = {https://github.com/JonasHeinickeBio/pyEuropePMC}
}

The literature itself comes from Europe PMC; please acknowledge it as your data source.

📄 License

PyEuropePMC is released under the MIT License. Articles you retrieve keep their own licences, which FullTextXMLParser.extract_license() reads from the XML.