Which integrations are available for this server?

Enables integration with LangChain agents for orchestrating medical AI workflows and building agentic applications on top of the MedX platform's diagnostic and healthcare capabilities. Provides access to OpenAI's API for AI-powered medical consultations, enabling clinical decision support, diagnostic assistance, and personalized healthcare recommendations through chat-based interactions.

How do I use MedX MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MedX MCP Server I have a persistent cough and fatigue, what could it be?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MedX MCP Server

AI-powered clinical agentic platform featuring our MedX-powered AI Agents and HealthOS, delivering advanced diagnostic support and personalized healthcare.

Overview

The MedX MCP Server provides a RESTful API for AI agents to access medical AI capabilities. It supports:

Advanced diagnostic support
Personalized healthcare recommendations
Clinical decision support
AI-powered medical consultations

Features

✅ RESTful API with Server-Sent Events (SSE) streaming
✅ Asynchronous tool execution
✅ Session management for conversations
✅ Idempotent requests
✅ Tool cancellation
✅ Health and readiness checks

Quick Start

Server Setup

# Install dependencies
pip install -r requirements.txt

# Set environment variables
export OPENAI_API_KEY="your-openai-key"
export MCP_SERVER_TOKEN="your-secret-token"

# Run server
python main.py

Server runs on http://localhost:8000 by default.

Client Usage

from client import MCPClient

# Initialize client
client = MCPClient(
    base_url="http://localhost:8000",
    auth_token="your-token"
)

# Discover capabilities
manifest = await client.discover()
print(manifest['description'])

# Call (simplified)
result = await client.call(
    messages=[{"role": "user", "content": "What is anemia?"}]
)

Documentation

CLIENT_USAGE_GUIDE.md - Complete client usage guide
API_DOCUMENTATION.md - Full API reference
API_QUICK_REFERENCE.md - Quick API cheat sheet
AGENT_INTEGRATION_GUIDE.md - How agents integrate with MCP server
ARCHITECTURE_EXPLANATION.md - Server architecture details

Client SDK

The project includes a Python client SDK in the client/ directory:

# Install client dependencies
pip install -r client/requirements.txt

# Use in your code
from client import MCPClient

See CLIENT_USAGE_GUIDE.md for complete examples.

Examples

examples/simple_client_example.py - Basic client usage
examples/langchain_integration_example.py - LangChain agent integration

API Endpoints

GET /mcp/manifest - Discover server capabilities and tools
POST /mcp/execute - Execute a tool
GET /mcp/stream/{call_id} - Stream results
POST /mcp/cancel/{call_id} - Cancel a call
GET /healthz - Health check
GET /readyz - Readiness check

Configuration

Environment variables:

OPENAI_API_KEY - OpenAI API key (required)
MCP_SERVER_TOKEN - Bearer token for authentication (default: "super-secret-token")
SERVER_HOST - Server host (default: "0.0.0.0")
SERVER_PORT - Server port (default: 8000)