Integrations
Supports loading environment variables from .env files for configuration, particularly for storing optional API keys used by the healthcare data services.
Used for version control and distribution of the Healthcare MCP Server codebase, enabling users to clone the repository for manual installation.
Hosts the Healthcare MCP Server repository, allowing users to access and clone the codebase for installation and deployment.
Healthcare MCP Server
A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools.
Overview
Healthcare MCP Server is a specialized server that implements the Model Context Protocol (MCP) to provide AI assistants with access to healthcare data and medical information tools. It enables AI models to retrieve accurate, up-to-date medical information from authoritative sources.
Features
- FDA Drug Information: Search and retrieve comprehensive drug information from the FDA database
- PubMed Research: Search medical literature from PubMed's database of scientific articles
- Health Topics: Access evidence-based health information from Health.gov
- Clinical Trials: Search for ongoing and completed clinical trials
- Medical Terminology: Look up ICD-10 codes and medical terminology definitions
- Caching: Efficient caching system with connection pooling to reduce API calls and improve performance
- Usage Tracking: Anonymous usage tracking to monitor API usage
- Error Handling: Robust error handling and logging
- Multiple Interfaces: Support for both stdio (for CLI) and HTTP/SSE interfaces
- API Documentation: Interactive API documentation with Swagger UI
- Comprehensive Testing: Extensive test suite with pytest and coverage reporting
Installation
Manual Installation
- Clone the repository:Copy
- Create a virtual environment:Copy
- Install dependencies:Copy
- Set up environment variables (optional):Copy
- Run the server:Copy
Usage
Running in Different Transport Modes
- stdio mode (default, for Cline):Copy
- HTTP/SSE mode (for web clients):Copy
Testing the Tools
You can test the MCP tools using the new pytest-based test suite:
For backward compatibility, you can still run the old tests:
API Reference
The Healthcare MCP Server provides both a programmatic API for direct integration and a RESTful HTTP API for web clients.
RESTful API Endpoints
When running in HTTP mode, the following endpoints are available:
Health Check
Returns the status of the server and its services.
FDA Drug Lookup
Parameters:
drug_name
: Name of the drug to search forsearch_type
: Type of information to retrievegeneral
: Basic drug information (default)label
: Drug labeling informationadverse_events
: Reported adverse events
Example Response:
PubMed Search
Parameters:
query
: Search query for medical literaturemax_results
: Maximum number of results to return (default: 5, max: 50)date_range
: Limit to articles published within years (e.g. '5' for last 5 years)
Example Response:
Health Topics
Parameters:
topic
: Health topic to search for informationlanguage
: Language for content (en or es, default: en)
Example Response:
Clinical Trials Search
Parameters:
condition
: Medical condition or disease to search forstatus
: Trial status (recruiting, completed, active, not_recruiting, or all)max_results
: Maximum number of results to return (default: 10, max: 100)
Example Response:
ICD-10 Code Lookup
Parameters:
code
: ICD-10 code to look up (optional if description is provided)description
: Medical condition description to search for (optional if code is provided)max_results
: Maximum number of results to return (default: 10, max: 50)
Example Response:
Generic Tool Execution
Request Body:
Programmatic API
When using the MCP server programmatically, the following functions are available:
FDA Drug Lookup
Parameters:
drug_name
: Name of the drug to search forsearch_type
: Type of information to retrievegeneral
: Basic drug information (default)label
: Drug labeling informationadverse_events
: Reported adverse events
PubMed Search
Parameters:
query
: Search query for medical literaturemax_results
: Maximum number of results to return (default: 5)date_range
: Limit to articles published within years (e.g. '5' for last 5 years)
Health Topics
Parameters:
topic
: Health topic to search for informationlanguage
: Language for content (en or es, default: en)
Clinical Trials Search
Parameters:
condition
: Medical condition or disease to search forstatus
: Trial status (recruiting, completed, active, not_recruiting, or all)max_results
: Maximum number of results to return
ICD-10 Code Lookup
Parameters:
code
: ICD-10 code to look up (optional if description is provided)description
: Medical condition description to search for (optional if code is provided)max_results
: Maximum number of results to return
Data Sources
This MCP server utilizes several publicly available healthcare APIs:
- FDA OpenFDA API
- PubMed E-utilities API
- Health.gov API
- ClinicalTrials.gov API
- NLM Clinical Table Search Service for ICD-10-CM
Premium Version (still being built)
This is the free version of Healthcare MCP Server with usage limits. For advanced features and higher usage limits, check out our premium version:
- Unlimited API calls
- Advanced healthcare data tools
- Custom integrations
- Priority support
License
MIT License
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A Model Context Protocol server providing AI assistants with access to healthcare data tools, including FDA drug information, PubMed research, health topics, clinical trials, and medical terminology lookup.
Related MCP Servers
- -securityAlicense-qualityA Model Context Protocol server that provides health data from the Senechal API to LLM applications, enabling AI assistants to access, analyze, and respond to personal health information.Last updated -PythonGPL 3.0
- -security-license-qualityA standalone Model Context Protocol server that enables AI models to access the Australian Pharmaceutical Benefits Scheme (PBS) API data, including medicine listings, pricing, and availability information.Last updated -1JavaScriptMIT License
- -securityAlicense-qualityA specialized Model Context Protocol server that enhances AI-assisted medical learning by connecting Claude Desktop to PubMed, NCBI Bookshelf, and user documents for searching, retrieving, and analyzing medical education content.Last updated -PythonMIT License
- AsecurityFlicenseAqualityA Model Context Protocol server implementation that provides structured, AI-friendly access to eRegulations data, making it easier for AI models to answer user questions about administrative procedures.Last updated -428TypeScript