pubcrawlSAFE
MCP server giving AI assistants verifiable access to PubMed, Europe PMC, US/UK drug labelling, and ClinicalTrials.gov. Built by PharmaTools.AI.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An [MCP server](https://modelcontextprotocol.io) that gives AI assistants access to PubMed, Europe PMC, FDA & UK drug labelling, and ClinicalTrials.gov.
A peer-reviewed pub crawl through the literature — the label — and the trial.
[](https://github.com/nickjlamb/pubcrawl/actions/workflows/build.yml) [](https://www.npmjs.com/package/@pharmatools/pubcrawl) [](https://www.npmjs.com/package/@pharmatools/pubcrawl) [](https://nodejs.org) [](https://registry.modelcontextprotocol.io/?q=pubcrawl) [](https://glama.ai/mcp/servers/nickjlamb/pubcrawl) [](https://mcpservers.org/servers/nickjlamb/pubcrawl) [](https://doi.org/10.5281/zenodo.22101559) [](LICENSE) [](CONTRIBUTING.md)
Quick start · Tools · Examples · Architecture · Roadmap · Contributing
✨ What is PubCrawl?
PubCrawl connects your AI assistant (Claude Desktop, Cursor, or any MCP-compatible client) directly to the primary sources clinicians and researchers actually use — so you can ask a qu
531c9b00292bOBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add pubcrawl --env NCBI_API_KEY=${NCBI_API_KEY} -- npx -y @pharmatools/[email protected]Exposed tools (15)
15 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
PubCrawl | read | Biomedical research tools: PubMed literature search, ClinicalTrials.gov, and US (FDA) / UK (eMC) drug labelling. Built by PharmaTools.AI. |
compare_labels | read | |
find_related | read | Find related articles for a given PubMed article. Returns similar papers ranked by relevance score using PubMed |
format_citation | read | Format a citation for a PubMed article in APA, Vancouver, Harvard, or BibTeX style. |
get_abstract | read | Get the full structured abstract and metadata for a PubMed article. Returns abstract sections (background, methods, results, conclusions), keywords, MeSH terms, and PMC ID. |
get_full_text | read | Get the full text of an open-access article from PubMed Central. Returns article sections, figure/table captions, and reference count. Only works for articles available in PMC. |
get_smpc | read | Get UK/EU Summary of Product Characteristics (SmPC) for a drug from eMC (medicines.org.uk). Returns structured labelling sections. |
get_trial | read | Get detailed information about a specific clinical trial from ClinicalTrials.gov. Returns eligibility criteria, study design, arms, outcomes, locations, and associated PubMed IDs. |
get_uspi | read | Get FDA US Prescribing Information (USPI) for a drug from openFDA (cited to DailyMed). Returns structured labelling sections with LOINC codes. |
resolve_drug_name | read | Convert a brand drug name to its generic name (or a generic to its US brand names), with drug class and common indications. Deterministic — sourced from RxNorm/openFDA, no AI. |
search_by_indication | read | Find drugs approved for a medical condition. Searches US FDA labelling for the condition, then checks UK (eMC) availability for each drug found. |
search_europepmc | read | |
search_pubmed | read | Search PubMed for biomedical literature. Returns article summaries with PMIDs, titles, authors, journals, and DOIs. |
search_trials | read | Search ClinicalTrials.gov for clinical trials. Filter by condition, intervention, status, and phase. Returns trial summaries with NCT IDs, status, sponsors, and enrollment info. |
trending_papers | read | Find recent/trending papers on a topic. Sorted by date, with optional filtering to high-impact journals. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (9 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
console.error(`PubCrawl MCP server running on http://0.0.0.0:${PORT}/mcp`);cheerio, fast-xml-parser, typebox, @types/node, typescript
@modelcontextprotocol/sdk, @pharmatools/drug-data, cheerio, dotenv, fast-xml-parser, zod, @types/node, @typescript-eslint/eslint-plugin
**NCBI Client** (`src/lib/ncbi.ts`) — Wraps the four E-utilities endpoints (`esearch`, `esummary`, `efetch`, `elink`) plus `pmidToPmcid`. All requests go through `rateLimitedFetch` (300ms delay withou
Gates applied: no_behavioural_pass.
531c9b00292bfull audit observations/trust-audit/mcp-server/nickjlamb__pubcrawl.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 531c9b00292b | SAFE | B | 89 | first audit |
Questions
What is the pubcrawl MCP server?
MCP server giving AI assistants verifiable access to PubMed, Europe PMC, US/UK drug labelling, and ClinicalTrials.gov. Built by PharmaTools.AI.
What tools does pubcrawl expose?
15 in total: 15 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is pubcrawl safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does pubcrawl need?
It reads NCBI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does pubcrawl run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @pharmatools/pubcrawl at 2.6.4.
How current is this page?
The grade is for one exact copy of the source (531c9b00292b), read on 2026-10-10. The repository is watched and re-audited when it changes.