About io.github.nickjlamb/pubcrawl
io.github.nickjlamb/pubcrawl is an MCP server in the Scraping category: pubMed literature search and US/UK drug labelling for AI assistants.
Install
claude mcp add io-github-nickjlamb-pubcrawl -- npx -y @pharmatools/pubcrawlnpx -y @pharmatools/pubcrawlThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
find_relatedFind similar articles using PubMed's neighbor algorithm, ranked by relevance score.
Parameters not published.
format_citationGenerate a formatted citation in APA, Vancouver, Harvard, or BibTeX style.
Parameters not published.
get_abstractGet the full structured abstract for an article — broken into labeled sections (background, methods, results, conclusions) with keywords and MeSH terms.
Parameters not published.
get_full_textRetrieve the full text of open-access articles from PubMed Central, with parsed sections, figure/table captions, and reference counts.
Parameters not published.
search_europepmcSearch Europe PMC — a broader corpus than PubMed that also indexes preprints (bioRxiv, medRxiv) and patents. Each result includes an abstract snippet, citation count, open-access status, and a preprint flag. Filter to preprints or open-access only.
Parameters not published.
search_pubmedSearch PubMed with filters for date range, article type, and sort order. Returns PMIDs, titles, authors, journals, and DOIs.
Parameters not published.
trending_papersFind recent papers on a topic, with optional filtering to high-impact journals (Nature, Science, Cell, NEJM, Lancet, JAMA, etc.).
Parameters not published.
Ask AI
Ask AI about io.github.nickjlamb/pubcrawl
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
PubCrawl
An MCP server that gives LLM clients access to PubMed, FDA drug labelling, UK medicines data, and ClinicalTrials.gov. A peer-reviewed pub crawl through the literature — the label — and the trial.
Built by PharmaTools.AI.
Tools
Literature
| Tool | What it does |
|---|---|
search_pubmed |
Search PubMed with filters for date range, article type, and sort order. Returns PMIDs, titles, authors, journals, and DOIs. |
get_abstract |
Get the full structured abstract for an article — broken into labeled sections (background, methods, results, conclusions) with keywords and MeSH terms. |
get_full_text |
Retrieve the full text of open-access articles from PubMed Central, with parsed sections, figure/table captions, and reference counts. |
find_related |
Find similar articles using PubMed's neighbor algorithm, ranked by relevance score. |
format_citation |
Generate a formatted citation in APA, Vancouver, Harvard, or BibTeX style. |
trending_papers |
Find recent papers on a topic, with optional filtering to high-impact journals (Nature, Science, Cell, NEJM, Lancet, JAMA, etc.). |
Drug Labelling
| Tool | What it does |
|---|---|
get_uspi |
Pull US Prescribing Information sections from DailyMed — indications, dosing, warnings, contraindications, and more. Parsed from FDA structured product labels. |
get_smpc |
Retrieve UK Summary of Product Characteristics from the eMC — the UK equivalent of US prescribing information, with numbered SmPC sections. |
compare_labels |
Side-by-side comparison of US (USPI) and UK (SmPC) labelling for the same drug. Spot regulatory differences in indications, warnings, and dosing. |
search_by_indication |
Find drugs approved for a medical condition. Searches FDA labelling via OpenFDA, then cross-references UK availability on the eMC. |
Clinical Trials
| Tool | What it does |
|---|---|
search_trials |
Search ClinicalTrials.gov for clinical trials. Filter by condition, intervention, recruitment status, and phase. Returns NCT IDs, sponsors, enrollment, and links. |
get_trial |
Get full details for a clinical trial by NCT ID — eligibility criteria, study design, arms, primary/secondary outcomes, locations, and associated PubMed IDs. |
Setup
Prerequisites
- Node.js 20+
- An MCP-compatible client (Claude Desktop, Cursor, etc.)
Install via npm
npm install -g @pharmatools/pubcrawl
Configure Claude Desktop
Add to your claude_desktop_config.json:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"pubcrawl": {
"command": "pubcrawl"
}
}
}
Restart Claude Desktop. PubCrawl will appear under + → Connectors.
Install from source
git clone https://github.com/nickjlamb/pubcrawl.git
cd pubcrawl
npm install
npm run build
Then point the config at the built file:
{
"mcpServers": {
"pubcrawl": {
"command": "node",
"args": ["/path/to/pubcrawl/dist/index.js"]
}
}
}
NCBI API key (optional)
Without an API key, requests are rate-limited to 3/second. With one, you get 10/second.
- Create a free NCBI account at https://www.ncbi.nlm.nih.gov/account/
- Go to Account Settings → API Key Management
- Add the key to your config:
{
"mcpServers": {
"pubcrawl": {
"command": "pubcrawl",
"env": {
"NCBI_API_KEY": "your_key_here"
}
}
}
}
Example prompts
Once connected, just ask naturally:
- "Search PubMed for recent clinical trials on semaglutide"
- "Get the abstract for PMID 38127654"
- "Find papers related to this one and format citations in APA"
- "What are the trending papers on CRISPR gene therapy this month?"
- "Get the full text of that paper from PMC"
- "Get the FDA prescribing information for metformin — just the indications and warnings"
- "Pull the UK SmPC for atorvastatin"
- "Compare US and UK labelling for lisinopril"
- "What drugs are approved for type 2 diabetes?"
- "Find recruiting Phase 3 trials for pembrolizumab in breast cancer"
- "Get details on clinical trial NCT03086486"
Development
npm run dev # TypeScript watch mode
npm run build # Compile to dist/
npm start # Run the server
License
MIT
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.