# pubcrawl **Category:** ๐Ÿ’ป Developer Tools **Repository:** https://github.com/nickjlamb/pubcrawl **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/pubcrawl ## Description PubMed literature search and US/UK drug labelling for AI assistants. ## Claude Desktop Quick Installation Heuristic fallback โ€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "pubcrawl": { "command": "npx", "args": ["-y","pubcrawl"] } } ``` ## Documentation & README
PubCrawl โ€” PubMed, drug labels, and clinical trials for AI assistants

**An [MCP server](https://modelcontextprotocol.io) that gives AI assistants access to PubMed, Europe PMC, FDA & UK drug labelling, and ClinicalTrials.gov.** _A peer-reviewed pub crawl through the literature โ€” the label โ€” and the trial._ [![ci](https://github.com/nickjlamb/pubcrawl/actions/workflows/build.yml/badge.svg)](https://github.com/nickjlamb/pubcrawl/actions/workflows/build.yml) [![npm](https://img.shields.io/npm/v/@pharmatools/pubcrawl?color=cb3837&logo=npm)](https://www.npmjs.com/package/@pharmatools/pubcrawl) [![downloads](https://img.shields.io/npm/dm/@pharmatools/pubcrawl?color=cb3837)](https://www.npmjs.com/package/@pharmatools/pubcrawl) [![node](https://img.shields.io/node/v/@pharmatools/pubcrawl?color=339933&logo=node.js&logoColor=white)](https://nodejs.org) [![MCP Registry](https://img.shields.io/badge/MCP_Registry-listed-6E56CF)](https://registry.modelcontextprotocol.io/?q=pubcrawl) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22101559.svg)](https://doi.org/10.5281/zenodo.22101559) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md) [Quick start](#-quick-start-60-seconds) ยท [Tools](#-tools) ยท [Examples](#-examples) ยท [Architecture](#-architecture) ยท [Roadmap](https://github.com/nickjlamb/pubcrawl/blob/HEAD/ROADMAP.md) ยท [Contributing](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CONTRIBUTING.md)
--- ## โœจ What is PubCrawl? PubCrawl connects your AI assistant (Claude Desktop, Cursor, or any MCP-compatible client) directly to the primary sources clinicians and researchers actually use โ€” so you can ask a question in plain English and get an answer grounded in **PubMed**, **Europe PMC**, **FDA/UK drug labelling**, and **ClinicalTrials.gov**, with real PMIDs, NCT IDs, and DOIs you can verify. Every tool is a thin, deterministic wrapper over an official API. Nothing is invented; every result cites its source. ### The thing no other MCP server does Ask **"compare US and UK labelling for semaglutide"** and PubCrawl pulls both live labels and maps equivalent sections โ€” US *Indications and Usage* โ†” UK *4.1 Therapeutic indications*, and so on โ€” so the differences are visible instead of assumed: ![Asking an MCP client to compare US and UK labelling for semaglutide: PubCrawl calls compare_labels, fetches the US Prescribing Information from openFDA/DailyMed and the UK SmPC from the eMC, and returns the two indication lists side by side โ€” three US indications including cardiovascular and renal risk reduction, against one UK indication, with the cardiovascular and renal outcomes appearing only as cross-references to sections 4.4, 4.5 and 5.1.](https://raw.githubusercontent.com/nickjlamb/pubcrawl/HEAD/docs/demo-compare-labels.gif) | | US Prescribing Information | UK SmPC | |---|---|---| | **Indications** | glycaemic control ยท **reduce risk of MACE** in T2D with established CVD ยท **reduce risk of sustained eGFR decline, ESKD and CV death** in T2D with CKD | glycaemic control only โ€” CV and renal outcomes appear as cross-references to ยง4.4/4.5/5.1, *not* as indications | | **Contraindications** | personal or family history of MTC or MEN 2 ยท hypersensitivity | hypersensitivity only | A cardiovascular claim that is on-label in the US promotes an unlicensed indication in the UK. If you write, review, or check medical copy for both markets, that gap is the whole job โ€” and `compare_labels` is the only MCP tool that surfaces it. ### Everything else - ๐Ÿ”ฌ **14 tools** across literature, drug labelling, and clinical trials - ๐Ÿงพ **Verifiable by design** โ€” results link back to DailyMed, the eMC, PubMed, and ClinicalTrials.gov - ๐Ÿ“ฐ **Preprints** via Europe PMC โ€” surface work ahead of formal publication - ๐Ÿ†“ **No API keys required** (an optional free NCBI key raises PubMed rate limits) - ๐Ÿงช Fully **typed, tested, and CI-checked** โ€” retrieval fidelity gated by [OpenGATE](https://github.com/nickjlamb/opengate) on every release Built by [PharmaTools.AI](https://pharmatools.ai). --- ## ๐Ÿš€ Quick start (60 seconds) **1. Add PubCrawl to your client config** โ€” no install step needed, `npx` fetches it on first run. For **Claude Desktop**, edit `claude_desktop_config.json`: - **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows:** `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "pubcrawl": { "command": "npx", "args": ["-y", "@pharmatools/pubcrawl"] } } } ``` **2. Restart your client.** PubCrawl appears under **+ โ†’ Connectors**. **3. Ask away:** > _"Compare the US and UK labelling for atorvastatin, and find recent Phase 3 trials for it."_ That's it. โ†’ [More examples](#-examples) ยท [API key & other options](#-configuration) --- ## ๐Ÿงฐ Tools ### ๐Ÿ“š 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. | | `search_europepmc` | Search Europe PMC โ€” 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. | | `get_abstract` | Get the full structured abstract for an article โ€” 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.). | ### ๐Ÿ’Š Drug labelling | Tool | What it does | |------|-------------| | `resolve_drug_name` | Convert a brand drug name to its generic (or a generic to its US brand names), with drug class and common indications. Deterministic, via RxNorm/openFDA โ€” no AI. | | `get_uspi` | Pull US Prescribing Information sections via openFDA (cited to DailyMed) โ€” indications, dosing, warnings, contraindications, and more. | | `get_smpc` | Retrieve UK Summary of Product Characteristics from the eMC โ€” 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. | ### ๐Ÿงซ 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 โ€” eligibility criteria, study design, arms, primary/secondary outcomes, locations, and associated PubMed IDs. | --- ## ๐Ÿ’ฌ Examples Once connected, just ask naturally: **Literature** - "Search PubMed for recent clinical trials on semaglutide." - "Search Europe PMC for preprints on GLP-1 receptor agonists, most cited first." - "Get the abstract for PMID 38127654, then find related papers and cite them all in Vancouver style." - "What are the trending papers on CRISPR gene therapy this month, high-impact journals only?" - "Pull the full text of that PMC article and summarise the methods section." **Drug labelling** - "Get the FDA prescribing information for metformin โ€” just the indications and warnings." - "Pull the UK SmPC for atorvastatin." - "Compare US and UK labelling for lisinopril and highlight the differences." - "What's the generic name and drug class for Ozempic?" - "What drugs are approved for type 2 diabetes in both the US and UK?" **Clinical trials** - "Find recruiting Phase 3 trials for pembrolizumab in breast cancer." - "Get the eligibility criteria and primary outcomes for NCT03086486." **Cross-source (where PubCrawl shines)** - "For semaglutide: summarise the US label's cardiovascular indication, then find the pivotal trial and its NEJM publication." --- ## ๐Ÿ— Architecture Three layers โ€” **tools** register the MCP interface, **lib clients** talk to each external API, and shared **cache** + **parsers** keep it fast and consistent. PubCrawl architecture: an MCP client connects over stdio or streamable HTTP to the PubCrawl server, whose 14 tools are grouped into literature, drug labelling and clinical trials. Each family calls the official APIs directly โ€” NCBI E-utilities, Europe PMC, openFDA and DailyMed, the UK eMC, and ClinicalTrials.gov โ€” behind a shared LRU cache, XML/JATS/SPL parsers and rate limits. Every result returns with its own identifier: PMID, NCT or DOI. No model sits in this path; nothing is invented. Each tool file exports a `register*Tool(server)` function with a zod schema and an async handler. All network calls are rate-limited, cached, and time-bounded. See [`CLAUDE.md`](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CLAUDE.md) for a full architecture walkthrough and [`CONTRIBUTING.md`](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CONTRIBUTING.md) to add a tool. --- ## ๐Ÿ”ง Configuration ### Install options ```bash # Zero-install (recommended): npx fetches it on demand โ€” see Quick start above. # Or install globally: npm install -g @pharmatools/pubcrawl # Config for a global install: # { "mcpServers": { "pubcrawl": { "command": "pubcrawl" } } } ``` ### NCBI API key (optional) Without a key, PubMed requests are limited to 3/second. A free key raises this to 10/second. 1. Create a free NCBI account at 2. Account Settings โ†’ API Key Management โ†’ create a key 3. Add it to your config: ```json { "mcpServers": { "pubcrawl": { "command": "npx", "args": ["-y", "@pharmatools/pubcrawl"], "env": { "NCBI_API_KEY": "your_key_here" } } } } ``` ### HTTP transport PubCrawl also ships a stateless Streamable HTTP transport for browser-based and hosted clients: ```bash npm run start:http # serves POST /mcp and GET /health on PORT (default 3000) ``` --- ## ๐Ÿ—บ Roadmap Highlights of what's planned โ€” see [`ROADMAP.md`](https://github.com/nickjlamb/pubcrawl/blob/HEAD/ROADMAP.md) for the full list. - `get_europepmc_fulltext` โ€” read preprints & OA articles surfaced by `search_europepmc` - `get_adverse_events` โ€” openFDA FAERS adverse-event lookups - EMA / EPAR labelling to complement the US + UK `compare_labels` - MeSH query helper for sharper PubMed searches - MCP **resources** & **prompts** for common review workflows Ideas welcome โ€” [open an issue](https://github.com/nickjlamb/pubcrawl/issues/new/choose). --- ## ๐Ÿ›  Development ```bash git clone https://github.com/nickjlamb/pubcrawl.git cd pubcrawl npm install npm run dev # TypeScript watch mode npm run build # compile to dist/ npm start # run the stdio server npm test # Vitest unit suite npm run lint # ESLint ``` Unit tests live in `tests/` and cover the parsing, caching, citation, and formatting logic with fixture payloads (no network calls). CI runs lint โ†’ test โ†’ build on every push and pull request. New to the codebase? Start with [`CONTRIBUTING.md`](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CONTRIBUTING.md). --- ## ๐Ÿ“ฆ Releases & changelog Versions follow [Semantic Versioning](https://semver.org). See the [**CHANGELOG**](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CHANGELOG.md) for a full history and [Releases](https://github.com/nickjlamb/pubcrawl/releases) for notes and assets. ## ๐Ÿค Contributing Contributions are welcome and appreciated โ€” bug reports, new data sources, new tools. Read the [contributing guide](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CONTRIBUTING.md) to get started, then [open an issue](https://github.com/nickjlamb/pubcrawl/issues/new/choose) or a pull request. ## ๐Ÿ“š Citation If PubCrawl supports work you publish, please cite it โ€” see [`CITATION.cff`](https://github.com/nickjlamb/pubcrawl/blob/HEAD/CITATION.cff), or: ```bibtex @software{lamb_pubcrawl, author = {Lamb, Nick}, title = {PubCrawl: verifiable biomedical literature, drug labelling and clinical trials for AI assistants}, year = {2026}, publisher = {Zenodo}, doi = {10.5281/zenodo.22101559}, url = {https://doi.org/10.5281/zenodo.22101559} } ``` --- ## ๐Ÿ“„ License [MIT](https://github.com/nickjlamb/pubcrawl/blob/HEAD/LICENSE) ยฉ [PharmaTools.AI](https://pharmatools.ai)
Data from NCBI E-utilities, Europe PMC, openFDA, DailyMed, the UK eMC, and ClinicalTrials.gov. PubCrawl is not affiliated with these providers.