Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
PyEuropePMC is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
34
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Search and analyse scientific literature across Europe PMC, PubMed, arXiv, and ClinicalTrials.gov
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user pyeuropepmc-mcp '--' uvx pyeuropepmc mcp
# 2 — ask your agent for something these tools do
# unified_search, search_papers, get_paper_details and 44 more
PyEuropePMC costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts PyEuropePMC as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user pyeuropepmc-mcp '--' uvx pyeuropepmc mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take 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 and the semantic_scholar source of unified_search; 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). Needed by the find_open_access tool only; there is no default.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
47 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Search across multiple literature sources (PubMed, arXiv, Semantic Scholar, OpenAlex, ClinicalTrials.gov) in parallel, with automatic cross-source deduplication.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query |
| sources | array | no | Sources to query, e.g. ['europepmc', 'arxiv', 'semantic_scholar', 'openalex', 'clinicaltrials']. Defaults to the server's configured source set. |
| limit | integer | no | Max results per source |
Search Europe PMC for papers (single source — prefer unified_search for multi-source coverage).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query |
| limit | integer | no | Number of results |
| sort | string | no | Sort order, e.g. 'cited' or 'date' |
| result_type | string | no | Europe PMC result type |
Get detailed paper information by PMID, PMCID, or DOI (Europe PMC).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | no | PubMed ID |
| pmcid | string | no | PMCID |
| doi | string | no | DOI |
Search for authors in Europe PMC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Author name or affiliation |
| limit | integer | no | Number of results |
Get papers that cite a given paper (Europe PMC).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | yes | PubMed ID |
| limit | integer | no | Max citing papers to return |
Walk the citation graph forward (cited-by), backward (references), or both, with configurable depth and a minimum-citation-count filter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| identifier | string | yes | Paper ID (PMID, DOI, or Semantic Scholar ID) |
| strategy | string | no | Snowball direction |
| max_papers | integer | no | Max papers per level |
| max_depth | integer | no | Recursion depth (0 = no limit) |
| min_citations | integer | no | Minimum citation count filter |
Search ClinicalTrials.gov for studies by condition, intervention, or free-text query.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Free-text search query |
| condition | string | no | Medical condition filter |
| intervention | string | no | Intervention/treatment filter |
| limit | integer | no | Max results |
| status | string | no | Recruitment status filter, e.g. ACTIVE, COMPLETED, RECRUITING |
Search the local SQLite FTS5 full-text index for papers whose full text matches a query.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Full-text search query |
| limit | integer | no | Max results |
| index_path | string | no | Path to the SQLite index file (optional) |
Extract figures, tables and supplementary files from a PMC Open Access article.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmcid | string | no | PMC ID of the article, e.g. PMC1234567 |
| pmid | string | no | PubMed ID (alternative to pmcid) |
| doi | string | no | DOI (alternative to pmcid) |
| include_tables | boolean | no | Include <table-wrap> elements |
| include_supplements | boolean | no | Include supplementary material |
Analyze citation context for a paper using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | yes | PubMed ID |
| context | string | no | Citation context description |
| task | string | no | Analysis task description |
Compare citations between two papers using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid1 | string | yes | PubMed ID of first paper |
| pmid2 | string | yes | PubMed ID of second paper |
| task | string | no | Comparison task description |
Summarize citation activity for a paper using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | yes | PubMed ID |
| citation_count | integer | no | Number of citations |
Automated paper screening with PRISMA-compliant criteria, using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query |
| inclusion_criteria | array | yes | Inclusion criteria |
| exclusion_criteria | array | yes | Exclusion criteria |
| limit | integer | no | Papers to screen |
Expand and analyze a research question using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| research_question | string | yes | Research question |
| time_frame | string | no | Time frame for literature search |
Preprint-specific quality assessment using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | yes | PubMed ID |
| preprint_server | string | no | Preprint server, e.g. bioRxiv, medRxiv |
Generate a comprehensive literature review using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| research_topic | string | yes | Research topic |
| key_concepts | array | yes | Key concepts to cover |
| time_frame | string | no | Time frame |
| excluded_topics | array | no | Topics to exclude from the review |
Build a knowledge graph from research literature using an LLM (requires an LLM provider).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| research_domain | string | yes | Research domain |
| entities | array | no | Key entities |
| relationships | array | no | Known relationships |
Parse a BibTeX string into structured entries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | BibTeX-formatted string |
Validate BibTeX entries for completeness and correctness.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | BibTeX string to validate |
Convert BibTeX entries to RIS format.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | BibTeX-formatted string |
Convert BibTeX entries to CSL-JSON format.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | yes | BibTeX-formatted string |
Resolve a DOI to bibliographic metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doi | string | yes | DOI to resolve |
Resolve a PubMed ID to bibliographic metadata.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pmid | string | yes | PubMed ID |
Merge multiple BibTeX libraries, deduplicating by DOI.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| libraries | array | yes | BibTeX-formatted strings to merge |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install PyEuropePMC or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 4.6.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest4d1ea75ff8f0d78c24f13e7bae51931aa6465389b1bb26345dbdf3efb97d5df6
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (47 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| unified_search | no tags | |
| search_papers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| count_papers | no tags | |
| get_paper_details | no tags | |
| search_authors | no tags | |
| get_paper_citations | no tags | |
| get_paper_references | no tags | |
| citation_snowball | no tags | |
| clinical_trial_search | no tags | |
| fulltext_index_query | no tags | |
| get_paper_fulltext | untrusted-input | untrusted-input: keyword "fetch" |
| paper_figures | no tags | |
| tag_paper_sentences | no tags | |
| epmc_status | no tags | |
| cache_status | no tags | |
| clear_cache | state-write | state-write: declares readOnlyHint: false |
| validate_query | no tags | |
| build_query | no tags | |
| translate_query | no tags | |
| evaluate_query | no tags | |
| export_papers | no tags | |
| get_papers_batch | no tags | |
| get_papers_fulltext_batch | no tags | |
| find_open_access | no tags | |
| get_paper_annotations | no tags | |
| find_papers_by_entity | no tags | |
| get_paper_data_links | no tags | |
| get_paper_lab_links | no tags | |
| enrich_paper | no tags | |
| pico_decompose | no tags | |
| mesh_expand | no tags | |
| analyze_search | no tags | |
| analyze_citations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| compare_citations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| summarize_citations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| paper_screening | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| research_question_analysis | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| preprint_analysis | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| literature_review | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| knowledge_graph | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| bib_parse_string | no tags | |
| bib_validate | no tags | |
| bib_to_ris | no tags | |
| bib_to_csl | no tags | |
| ref_resolve_doi | no tags | |
| ref_resolve_pmid | no tags | |
| bib_merge | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest4d1ea75ff8f0d78c
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 4.6.0. Pin a release below and the command asks for exactly that one.
4.6.0
28 Oct 2026
latestNo release note was published with this version.
4.5.0
26 Oct 2026
No release note was published with this version.
4.4.0
26 Oct 2026
No release note was published with this version.
4.2.0
22 Oct 2026
No release note was published with this version.
4.1.0
21 Oct 2026
No release note was published with this version.
4.0.1
21 Oct 2026
No release note was published with this version.
3.9.0
21 Oct 2026
No release note was published with this version.
3.8.0
19 Oct 2026
No release note was published with this version.
3.6.0
19 Oct 2026
No release note was published with this version.
3.2.0
19 Oct 2026
No release note was published with this version.
3.1.0
18 Oct 2026
No release note was published with this version.
3.0.0
17 Sep 2026
No release note was published with this version.
2.2.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish PyEuropePMC can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.