healthcare -public

Healthcare MCP Server provides AI-assisted access to a curated set of medical information tools via the Model Context Protocol. The server exposes capabilities for FDA drug information lookup, PubMed literature search, Health Topics queries, clinical trials search, ICD-10 terminology lookup, medRxiv search, a BMI calculator, NCBI Bookshelf search, DICOM metadata extraction, and robust caching and usage tracking. It supports both standard MCP stdio interfaces for CLI clients and HTTP/SSE interfaces for web-based clients, with a Swagger-driven API documentation surface when running in HTTP mode. You can test tools directly using the built-in test scripts (e.g., test:fda for FDA lookups, test:pubmed for PubMed searches, test:health for health topics, etc.).

Prerequisites: Node.js installed, npm available, and optional API keys for external data sources.

Option 1: DXT Extension (Recommended)

1. Download healthcare-mcp.dxt from the repository.
2. Open with your compatible MCP client (e.g., Claude Desktop).
3. Follow the installation prompts and configure optional settings in the GUI.

Option 2: Installing via Smithery To install Healthcare Data and Medical Information Server via Smithery:

npx -y @smithery/cli install @Cicatriiz/healthcare-mcp-public --client claude

Option 3: npm Installation

1. Install the package:

npm install healthcare-mcp

2. Run the server:

npx healthcare-mcp

Option 4: Manual Installation from Source

1. Clone the repository:

git clone https://github.com/Cicatriiz/healthcare-mcp-public.git
cd healthcare-mcp-public/server

2. Install dependencies:

npm install

3. Set up environment variables (optional):

# Create .env file from example
cp .env.example .env
# Edit .env with your API keys (optional)

4. Run the server:

npm start

Tips and notes:

• The DXT extension offers a quick install path for Claude Desktop users and other MCP clients; use it if you want a one-click setup.
• If running locally without a GUI, you can start in stdio mode using npm start and switch to HTTP/SSE mode with npm run server:http when needed.
• You can customize external data sources by providing API keys as environment variables; ensure you keep keys secure and do not commit them.
• The server includes extensive tests (npm test, npm run test:<tool>) to verify each tool’s behavior before production usage.
• For production deployments, consider enabling caching and usage tracking in your environment to optimize performance and monitor usage patterns.