Pubcrawl MCP Server

An MCP server that gives AI assistants access to PubMed, Europe PMC, FDA & UK drug labelling, and ClinicalTrials.gov. It runs locally over stdio via the published package.

People who work with biomedical, literature search and ncbi and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-01 · ★ 14 · #27 OF 71 MAINTAINED SCIENCE & HEALTH · VERIFIED 2026-09-18

MIT · TypeScript servers · how we verify → /methodology

01 · Install Pubcrawl

before you install - you'll need

NCBI_API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

claude mcp add nickjlamb-pubcrawl -- npx -y @pharmatools/pubcrawl

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "nickjlamb-pubcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@pharmatools/pubcrawl"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

npm package @pharmatools/pubcrawl - the @pharmatools scope differs from the repo owner (nickjlamb); confirm it's the project's official package

registry namespace io.github.nickjlamb is GitHub-verified and matches the repo owner

03 · What Pubcrawl can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v2.5.1 · 2026-08-25

Docs release. The README now opens with compare_labels - the one thing no other MCP server does - using a worked semaglutide example: the cardiovascular indication is on-label in the US and unlicensed in the UK. New…

v2.5.0 · 2026-07-30

v2.5.0 - consistent author lists, release-gated retrieval · Changed · search_europepmc now returns authors as a string[], matching search_pubmed - any code consuming both tools now gets a consistent shape. Surfaced by…

v2.4.0 · 2026-07-30

v2.4.0 - Europe PMC, tests, and a project glow-up · Highlights · New tool search_europepmc - search Europe PMC alongside PubMed: preprints (bioRxiv, medRxiv) and patents, with abstract snippets, citation counts…

04 · Who maintains Pubcrawl

pubcrawl is maintained by nickjlamb. We track 4 MCP servers from nickjlamb - 4 actively maintained, 24 combined GitHub stars, oldest repo from Feb 2026. Full record: all servers from nickjlamb.

redacta-mcp Pseudonymise and restore patient identifiers & PII in text - local, HIPAA Safe Harbor mode. ★ 8

05 · Facts

repository: github.com/nickjlamb/pubcrawl
category: science & health - ranked #27 of 71 actively-maintained science & health servers as of 2026-09-18.
release cadence: 3 releases in the last 90 days (latest 2026-08-25)
registry: io.github.nickjlamb/pubcrawl (active, first published 2026-02-16 · 3 versions)
packages: npm:@pharmatools/pubcrawl

06 · Pubcrawl FAQ

What is Pubcrawl?

An MCP server that gives AI assistants access to PubMed, Europe PMC, FDA & UK drug labelling, and ClinicalTrials.gov. It runs locally over stdio via the published package.

Is Pubcrawl still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-01 and it shipped 3 releases in the last 90 days. We re-verify nightly.

How do I install Pubcrawl?

Run `npx -y @pharmatools/pubcrawl`. The README documents one environment variable (NCBI_API_KEY) to set first. You can also paste the ready-made client config above.

Does Pubcrawl run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Pubcrawl

Alternatives to Pubcrawl

Maintained science & health servers if Pubcrawl isn't the fit.

More science & health MCP servers · Redacta MCP · DICOM/HL7/FHIR Interoperability MCP Server · Omophub MCP · Kaiord · Patsnap Patent & Literature Search

More TypeScript MCP servers · Swissgroceries MCP · Agentic Ads · Nifra docs · UI Beats · see all