StatPearls
About
Fetches peer-reviewed medical and disease information from StatPearls.
Details
- Author
- jpoles1
- Categories
- Search, Other, Knowledge Base
Jump to
Setup
Install StatPearls in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/jpoles1/statpearls-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
AModel Context Protocol (MCP)server that fetches disease information fromStatPearls, a trusted source of peer-reviewed medical content.
Give your AI system a relaible source of medical knowledge for its next conversation.
- Searches for diseases and medical conditions on StatPearls
- Retrieve comprehensive, reliable medical information from StatPearls
- Convert HTML content to well-formatted Markdown to make it AI-friendly
- Integrates with AI models via the Model Context Protocol
If you don't already have a Model Context Protocol (MCP) client:
If you are a casual user, you can useClaude Desktopto get started using MCP servers. It is a free and open-source desktop application that allows you to run MCP servers locally and connect to them.
If you are a power user/developer, I recommend using VSCode with theRooCodeextension which enables you to connect inMCP serversto your development environment for infinite possibilities!
Once you have an MCP-capable AI client, you can run this server locally.
The easiest way to get up and running is to download the appropriate executable/binary for your OS from thereleases page. This will give you a self-contained executable that you can run without any additional setup.
Place this executable in a directory of your choice. Then simply add the following to yourmcp_settings.jsonfile:
{ "mcpServers": { ... "statpearls": { "command": "{path_to_executable_here}\\statpearls-mcp.exe" }, ... } } #### For Mac/Linux:
To install statpearls-mcp for Claude Desktop automatically viaSmithery:
npx -y @smithery/cli install @jpoles1/statpearls-mcp --client claude
You can also run the server from source. This requiresBunto be installed on your system.
- Clone the repository
- Install dependencies (bun install)
- Compile the server (bun run build)
- Now you can add the server to yourmcp_settings.jsonfile:
{ "mcpServers": { ... "statpearls": { "command": "node", "args": [ "{path_to_proj_here}/dist/index.js" ] }, ... } }
- statpearls_disease_info: Fetches comprehensive, reliable medical information about diseases from StatPearls.
{ "query": "diabetes", "format_options": { "includeToc": true, "maxLength": 50000 } }
- query: Disease or medical condition to search for (required)
- format_options: Optional formatting preferences
- includeToc: Whether to include a table of contents (default: true)
- maxLength: Maximum length of the returned content in characters (default: 50000)
The tool returns formatted Markdown content with:
- Title and source information
- Table of contents (optional)
- Structured sections including etiology, epidemiology, pathophysiology, clinical features, diagnosis, treatment, and prognosis (when available)
statpearls-mcp/ ├── src/ # Source code │ ├── index.ts # Main entry point and server setup │ ├── test-html-parser.ts # Test utility for HTML parser │ ├── test-statpearls-parser.ts # Test utility for StatPearls parser │ ├── testrun.ts # Test runner utility │ ├── tools/ # Tool definitions and handlers │ │ └── statpearls.ts # StatPearls tool definition and handler │ ├── services/ # Core functionality services │ │ ├── search.ts # Search functionality │ │ ├── content.ts # Content retrieval and processing │ │ └── markdown.ts # HTML to Markdown conversion │ ├── types/ # Type definitions │ │ ├── index.ts # Common type definitions │ │ └── statpearls.ts # StatPearls-specific type definitions │ └── utils/ # Utility functions │ ├── html.ts # HTML parsing utilities │ ├── error.ts # Error handling utilities │ └── statpearls-parser.ts # StatPearls content parsing utilities ├── scripts/ # Build and utility scripts │ ├── build.ts # Build script for creating Node.js compatible bundle │ ├── compile.ts # Script for compiling executables │ ├── release.ts # Script for handling releases │ └── version.ts # Script for managing versioning ├── dist/ # Build output directory (not in repository) ├── package.json # Project configuration and dependencies ├── tsconfig.json # TypeScript configuration ├── bun.lock # Bun dependency lock file ├── README.md # Main project documentation └── RELEASE-PROCESS.md # Documentation for release process
The build process creates a single JavaScript file that can run with vanilla Node.js:
# Production build bun run build # or bun run build:prod # Development build bun run build:dev
This creates a bundled file atdist/index.jsthat includes all dependencies.
You can compile platform-specific executables using Bun's compilation feature:
# Compile for all platforms bun run compile:all # Compile for specific platforms bun run compile:linux bun run compile:windows bun run compile:mac
This creates executable files in thedistdirectory:
- statpearls-mcp(default executable)
- statpearls-mcp-linux-x64(Linux)
- statpearls-mcp-windows-x64.exe(Windows)
- statpearls-mcp-darwin-x64(macOS)
The release process handles versioning, building, compiling, and Git operations:
# Release a patch version (bug fixes) bun run release:patch # Release a minor version (new features, backward compatible) bun run release:minor # Release a major version (breaking changes) bun run release:major```
- Updates the version in package.json
- Builds the distribution file
- Compiles executables for all platforms
- Creates a Git commit with the version number
- Creates a Git tag for the version
- Pushes the commit and tag to GitHub
The project follows semantic versioning. You can check the current version with:
This project is licensed under the MIT License - see the LICENSE file for details.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
A server for searching, retrieving, and analyzing articles from the PubMed database.
Search PubMed and summarize biomedical literature — designed for AI health agents.
Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.
Multi-source MCP server: arXiv + PubMed + GitHub + HuggingFace + openFDA 510(k)/Recalls. Newspaper-style briefings, per-domain tuning, sandbox-safe Python launcher.
Unified access to global medical terminologies: ICD-11, SNOMED CT, LOINC, RxNorm, MeSH. 27 tools for medical coding, terminology lookup, and crosswalk mappings.
Medical terminology intelligence for AI agents — ICD-10-CM lookup, MedDRA hierarchy and SOC mapping, RxNorm drug concepts, CTCAE v5.0 grading, and cross-terminology mapping.
Free hypertrophy knowledge base - based exclusively on scientific papers.
ICH guideline lookup, CTD/eCTD module mapping, submission checklists, and FDA/EMA deficiency guidance for regulatory affairs teams.
SkinKnowledgeBase Skincare Question and Answer MCP
Source-backed skincare question-answering with cited ingredients, products, concerns, side effects, sources, and comparison context.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
