MedixHub Model Context Protocol (MCP) Server
LocalAbout MedixHub Model Context Protocol (MCP) Server
MedixHub Model Context Protocol (MCP) Server exposes medical and healthcare API functions for applications using MCP, including tools for Open Targets, FDA drug labels, and Monarch biomedical data. It supports parameter validation and authenticated access.
Key features
- 01Open Targets GraphQL queries
- 02FDA drug label search
- 03Generic and brand name mapping
- 04Monarch biomedical entity search
- 05Parameter validation
- 06API key and JWT authentication
Use cases
- 01Looking up drug labels and adverse reactions
- 02Exploring disease and target relationships
- 03Finding diseases linked to phenotypes
- 04Searching genes and biomedical entities
MCP support
Exposes standardized, parameter-validated healthcare functions to MCP clients, including Open Targets, FDA drug information, and Monarch searches. Function metadata is available through discovery endpoints.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMedixHub Model Context Protocol (MCP) Server
A Model Context Protocol (MCP) server with integrated medical and healthcare API access through MedixHub.
Features
- Pure JavaScript implementation
- Exposes functions with standardized MCP metadata
- Executes functions with parameter validation
- Seamlessly integrates with LLMs like Ollama
- Secure API endpoints with authentication
- Supports streaming responses
Implemented Functions
The server includes JavaScript implementations of these functions:
- executeOpenTargetQuery - Executes GraphQL queries against the OpenTarget API
- FDADrugLabelSearch - Retrieves drug information from the FDA database
- get_drug_generic_name - Maps between generic and brand drug names
- MonarchSearch - Searches the Monarch database for genes, diseases, or phenotypes
- MonarchDiseasesForMultiplePhenotypes - Finds diseases matching multiple phenotypes
OpenTarget Functions
- Disease information lookup
- Drug details and associations
- Target (gene/protein) information
- Disease-target associations
- Drug-disease relationships
FDA Drug Label Functions
- Drug information search
- Generic and brand name mapping
- Adverse reactions lookup
- Drug interactions search
Monarch Database Functions
- Biomedical entity search
- Disease-phenotype associations
- Gene-phenotype relationships
- Multi-phenotype disease finder
Getting Started
Prerequisites
- Node.js 14 or later
- npm or yarn
Installation
- Clone the repository
git clone https://github.com/yourusername/medixhub-mcp-server.git
cd medixhub-mcp-server
- Install dependencies
npm install
- Configure environment variables
cp .env.example .env
# Edit .env with your settings
- Start the server
npm start
For development with auto-reload:
npm run dev
Usage
Execute API
Use the /execute endpoint to run any registered MedixHub function:
POST /execute
Content-Type: application/json
{
"name": "queryFDADrugLabel",
"parameters": {
"searchFields": {
"drug_name": ["openfda.brand_name", "openfda.generic_name"]
},
"returnFields": ["openfda.generic_name", "warnings"],
"arguments": {
"drug_name": "ibuprofen",
"limit": 1
}
}
}
Direct MedixHub API
Use the /medixhub endpoints for direct API access:
/medixhub/opentargets/medixhub/opentargets-genetics/medixhub/drug-by-name/medixhub/fda-drug-label/medixhub/drug-generic-name/medixhub/monarch/medixhub/diseases-for-phenotypes
Function Metadata
Get information about available functions:
/functions- All available functions/functions/medixhub- MedixHub-specific functions/functions/category/:category- Functions by category
API Documentation
Full API documentation is available at /functions/medixhub
Development
Project Structure
medixhub-mcp-server/
├── server.js # Main server file
├── src/
│ ├── medixhub/ # MedixHub integration
│ ├── middleware/ # Middleware
│ ├── routes/ # Route handlers
│ └── services/ # Services
├── examples/ # Usage examples
└── tests/ # Test suite
Adding New Functions
To add a new function to the registry:
const { registerFunction } = require('./src/services/functionRegistry');
registerFunction('myNewFunction', {
name: 'myNewFunction',
description: 'Description of what this function does',
parameters: {
// Parameter schema
},
function: async (params) => {
// Implementation
return result;
}
});
Running Tests
npm test
Authentication
The server supports two authentication methods:
- API Keys: Simple key-based authentication
- JWT Tokens: More granular access control
In production mode, authentication is required for all endpoints except function discovery.
Environment Variables
Configure the server through the following environment variables:
PORT: Server port (default: 3000)NODE_ENV: Environment ('development' or 'production')OLLAMA_API_URL: URL for Ollama APIAPI_KEYS: Comma-separated list of valid API keysFDA_API_KEY: API key for FDA drug database
See .env.example for all available options.
Performance Considerations
- The server uses asynchronous processing for all API calls
- Rate limiting is enabled to prevent abuse
- Timeout handling prevents hanging requests
- Memory usage is optimized by processing streams efficiently
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.