PubCrawl — Real PubMed Access for AI

The Problem

Your AI tools don’t have access to PubMed.

When you ask an AI about a paper, it’s usually working from memory — training data that’s months or years out of date. It’ll confidently cite papers that don’t exist.

Most AI tools can’t search by MeSH term, filter by study type, or tell you what was published last week. For anyone working in healthcare, pharma, or biomedical research, that’s not good enough. PubCrawl gives reliable PubMed access to all of them.

× Hallucinated doi:10.1016/j.cell.2024.08.142

✓ Verified doi:10.1016/j.media.2023.102802

What PubCrawl Does

Fourteen tools. One install. Literature, labels, and trials.

PubCrawl is an MCP server — a plugin that gives AI assistants real-time access to PubMed, Europe PMC, FDA drug labelling, UK medicines data, and ClinicalTrials.gov. Install it once, and your AI can:

Search PubMed

Full query support with filters for date range, article type, and sort order. PubMed’s own search syntax works too — Boolean operators, field tags, all of it.

Search Europe PMC

Go beyond PubMed to preprints (bioRxiv, medRxiv) and patents. Every result carries an abstract, citation count, open-access status, and a preprint flag — filter to preprints or open access only.

Pull Structured Abstracts

Background, methods, results, and conclusions parsed into sections. Plus MeSH terms, keywords, and links to the full text where available.

Retrieve Full Text

For open-access papers in PubMed Central, extract the complete article: sections, figure captions, table descriptions, and reference counts.

Find Related Papers

Surface related work using NCBI’s citation-aware relevance scoring. Follow threads through the literature without manual searching.

Format Citations

APA, Vancouver, Harvard, or BibTeX — generated from real metadata, not guesswork.

Track What’s New

Find recent papers in any topic area, with optional filtering to high-impact journals. Stay current without setting up alerts.

Resolve Drug Names

Convert a brand name to its generic — or a generic to its US brand names — with drug class and common indications. Deterministic, via RxNorm. No guesswork.

US Prescribing Information

Pull FDA-approved USPI sections via openFDA, cited to DailyMed — indications, dosing, warnings, contraindications, and more.

UK SmPC Data

Retrieve Summary of Product Characteristics from the eMC — the UK equivalent of US prescribing information, with numbered SmPC sections.

Compare US/UK Labels

Side-by-side comparison of FDA and MHRA/EMA labelling for the same drug. Spot regulatory differences in indications, warnings, and dosing.

Search by Indication

Find drugs approved for a medical condition via OpenFDA, then cross-reference UK availability on the eMC. One query, both markets.

Search Clinical Trials

Query ClinicalTrials.gov by condition, intervention, phase, and recruitment status. Find what’s recruiting, completed, or in progress.

Get Trial Details

Full study detail by NCT ID — eligibility criteria, study design, arms, outcomes, locations, and linked PubMed publications.

How It Works

Plug in and go.

PubCrawl uses the Model Context Protocol — an open standard created by Anthropic that lets AI applications call external tools securely. Think of it as a USB port for AI: plug in PubCrawl, and any MCP-compatible client gains biomedical literature and drug data superpowers.

1 You ask your AI something about the literature

2 The AI recognises it needs PubMed and calls PubCrawl

3 PubCrawl queries NCBI, Europe PMC, OpenFDA, DailyMed, the eMC, RxNorm, or ClinicalTrials.gov in real time

4 Results come back structured and verified — real PMIDs, real DOIs, real data

5 Your AI uses the results to give you a grounded, accurate answer

No API keys required. No subscription. Just install and go.

See It in Action

From question to verified citations.

Claude Desktop

NL

What’s the latest on in vivo CAR-T cell engineering? Any 2026 papers?

C

I’ll search PubMed for recent CAR-T research.

◆ search_pubmed — query: "CAR-T cell therapy" AND "in vivo", sort: date, minDate: 2026/01/01

In vivo chimeric antigen receptor (CAR)-T cell therapy.

Bot A et al. · Nature Reviews Drug Discovery · 2026

PMID: 41028170 · doi:10.1038/s41573-025-01291-5

CD19 CAR T-Cell Therapy for Autoimmune Hemolytic Anemia.

Li R et al. · N Engl J Med · 2026

PMID: 41534043 · doi:10.1056/NEJMoa2509820

C

Here are the top results. The Bot et al. review in Nature Reviews Drug Discovery covers in vivo CAR-T engineering approaches, and the Li et al. NEJM paper reports sustained remission in autoimmune hemolytic anemia. Want me to pull the full abstract for either?

Claude Desktop

NL

Compare the US and UK labelling for atorvastatin — just the indications and warnings sections.

C

I’ll pull the FDA prescribing information and the UK SmPC for atorvastatin and compare those sections.

◆ compare_labels — drug: "atorvastatin", sections: ["indications", "warnings"]

Indications

US (USPI): Hyperlipidemia, heterozygous familial hypercholesterolemia (10–17 years), primary prevention of CV disease…

UK (SmPC): Hypercholesterolaemia, prevention of cardiovascular events in high-risk patients, familial hypercholesterolaemia…

Warnings

US (USPI): Skeletal muscle effects (myopathy/rhabdomyolysis), liver enzyme abnormalities, risk in pregnancy…

UK (SmPC): Hepatic effects, skeletal muscle effects, interstitial lung disease, diabetes mellitus risk…

C

Key difference: the UK SmPC explicitly calls out diabetes mellitus risk and interstitial lung disease in warnings, while the US PI doesn’t highlight these in the same section. Want the full text of either label?

Claude Desktop

NL

Are there any recruiting Phase 3 trials for pembrolizumab in breast cancer?

C

I’ll search ClinicalTrials.gov for recruiting Phase 3 pembrolizumab trials in breast cancer.

◆ search_trials — condition: "breast cancer", intervention: "pembrolizumab", phase: PHASE3, status: RECRUITING

Pembrolizumab + Chemotherapy in Triple-Negative Breast Cancer

Phase 3 · Recruiting · n=1,200 · Merck Sharp & Dohme

NCT03036488 · clinicaltrials.gov/study/NCT03036488

Neoadjuvant Pembrolizumab in Early-Stage Breast Cancer

Phase 3 · Recruiting · n=800 · Merck Sharp & Dohme

NCT04191135 · clinicaltrials.gov/study/NCT04191135

C

I found several active Phase 3 trials. The KEYNOTE studies are the largest, investigating pembrolizumab combinations in triple-negative and early-stage breast cancer. Want me to pull full details on any of these?

Literature Search

Built With

Solid foundations.

TypeScript · Type-safe and maintainable
MCP SDK · Anthropic’s official protocol
NCBI E-utilities · PubMed’s own API
Europe PMC · Preprints & wider open access
OpenFDA · FDA drug labelling search
DailyMed · US structured product labels
eMC · UK medicines compendium
RxNorm · Drug name normalisation
ClinicalTrials.gov · Clinical trials registry
fast-xml-parser · PubMed XML handling
LRU Cache · Smart rate-limit-aware caching

Retrieval is only useful if it’s faithful. PubCrawl’s record parsing is regression-gated by OpenGATE, our open-source evaluation framework: known records in, checks that every author, year, and abstract comes back intact against the source — so a parser change can’t silently corrupt the evidence your AI grounds on. Gated on every release across PubMed and Europe PMC — 100% fidelity.

Who It’s For

Built for people who need the literature to be right.

Medical Writers

Verify references instantly. Pull structured abstracts without leaving your writing environment. Generate properly formatted citations in any style.

Researchers

Explore the literature conversationally. Follow citation trails. Stay on top of new publications in your field.

Healthcare AI Teams

Ground your models in real evidence. Build retrieval-augmented workflows that cite actual papers.

Regulatory & Pharma Teams

Compare US and UK drug labelling side by side. Search by indication across FDA and eMC. Ground regulatory intelligence in real prescribing data.

Anyone Tired of Hallucinated Citations

If you’ve ever clicked a DOI that led nowhere, PubCrawl is for you.

Install

Up and running in minutes.

Works with Claude Desktop, Cursor, and any MCP-compatible client.

Prefer zero install? Skip the terminal step and set "command": "npx" with "args": ["-y", "@pharmatools/pubcrawl"] instead of "command": "pubcrawl" in the config below — npx fetches it on first run.

terminal

npm install -g @pharmatools/pubcrawl

Then add to your claude_desktop_config.json:

claude_desktop_config.json

{
  "mcpServers": {
    "pubcrawl": {
      "command": "pubcrawl"
    }
  }
}

Restart Claude Desktop. Full setup instructions on GitHub.

npm Package → GitHub Repository →

About

A PharmaTools.AI project.

PubCrawl is part of a growing suite of tools built at the intersection of AI and healthcare. It’s open source, free to use, and built by someone who’s spent 25 years turning complex medical information into something useful.

Because the literature, the label, and the trial are too important to hallucinate.