Health and biology · MCP server
Pubcrawl: MCP server, setup and security
Pubcrawl is an open-source MCP server that lets an AI agent search biomedical literature and compare US and UK drug labels. Its repository has 15 stars and its last commit is from October 16, 2026 and it is licensed under MIT.
What Pubcrawl does
According to its repository: “PubMed, Europe PMC (including preprints), FDA/DailyMed and UK eMC drug labelling, and ClinicalTrials.gov for AI assistants, including side-by-side US vs UK label comparison. Every result cites its PMID, NCT ID or DOI; no API key required.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Pubcrawl is listed under Health and biology, a category of 37 servers in the directory, where it ranks #25 by stars.
Topics declared by the repository: biomedical, literature-search, llm-tools, ncbi, pubmed, clinical-trials.
Installing and connecting Pubcrawl
Distribution modes declared in the official MCP registry:
- npm package (Node.js, usually started with
npx)
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript.
The registry lists one secret variable to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Pubcrawl:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on February 15, 2026, the nickjlamb/pubcrawl repository has 15 stars and 3 forks, with 0 open issues. It has more stars than 33% of the servers in the directory. It received changes this month. Version published in the registry: 2.6.4 (October 6, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Pubcrawl is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- Medplum2.8K ★
- Pyscn1.1K ★
- Biomcp662 ★
- FHIR MCP Server (wso2)136 ★
- HealthChain229 ★
- Google health MCP72 ★
Learn more
Frequently asked questions
How do I install Pubcrawl?
Pubcrawl is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of nickjlamb/pubcrawl.
Is Pubcrawl free?
The code is published under the MIT licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is Pubcrawl safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by nickjlamb on GitHub. Check who maintains it before giving it access.
What are the alternatives to Pubcrawl?
In the same category: Medplum, Pyscn, Biomcp, and FHIR MCP Server (wso2). Medplum and Pyscn score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score