MCP server · Research
PubCrawl MCP server
by nickjlamb
Lets your AI search medical studies, drug labels and clinical trials, with real citations.
PubCrawl is a helper that connects your AI assistant to the medical sources doctors and researchers actually use. You ask a question in plain English, and it looks things up in PubMed, Europe PMC, US and UK drug labels, and ClinicalTrials.gov. It is handy for anyone who reads medical literature or checks drug information for a living, or just out of curiosity.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you using what it already learned. An MCP server is a small helper program that gives your AI a new skill or a connection to an outside service. This one connects your AI to medical databases like PubMed and the UK drug label site, so it can look things up there when you ask. You do not need to know how it works inside, you just add it once and then talk to your AI as usual.
What this MCP server does
You ask your AI something like find recent studies on a drug, or compare the US and UK labels for it. Your AI passes that request to PubCrawl, which goes and searches the real source, such as PubMed or the FDA label database. PubCrawl brings back the matching records with their ID numbers, titles, and short summaries. Your AI then reads that back to you in the chat, in normal sentences. Every result points to a real source you can check yourself.
What you can do with it
- Search PubMed for recent studies on a topic or drug
- Search Europe PMC for preprints and open access papers
- Get the full abstract of an article by its PMID
- Pull the US prescribing information for a drug
- Pull the UK label (SmPC) for the same drug
- Compare US and UK labels side by side
- Find clinical trials by condition, phase, or status
- Get the eligibility rules and outcomes for a trial by its NCT ID
Try asking your AI
- “Search PubMed for recent clinical trials on semaglutide”
- “Compare the US and UK labelling for atorvastatin and highlight the differences”
- “What is the generic name and drug class for Ozempic”
- “Find recruiting Phase 3 trials for pembrolizumab in breast cancer”
- “Get the abstract for PMID 38127654 and cite it in Vancouver style”
What it gives back to you
You get back lists of studies with their PMIDs, titles, authors, journals and DOIs, or drug label sections, or trial details with NCT IDs and sponsors. For a label comparison, you get the two sides lined up so you can see where they differ. Everything comes back as text in the chat, and each item points to the original source so you can verify it.
Before you start
What you need
- An AI assistant that supports MCP, such as Claude Desktop or Cursor
- Node.js installed on your computer (the free program that runs npx)
- Optional: a free NCBI account and API key if you want faster PubMed searches
Good to know
It only reads from public medical databases, so it does not change or delete anything, but the answers are only as good as the source records and you should always check the original label or paper before relying on it.
Install it with your AI
Add PubCrawl MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check PubCrawl MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.
Who it's for
Medical writers, clinicians, researchers, regulatory affairs staff, and anyone who regularly checks drug labels or reads medical studies.
