Epic Healthcare MCP Server

Epic Healthcare MCP Server

Enables AI assistants to securely access Epic Healthcare Systems patient data through FHIR R4 API integration. Provides tools for searching patients, retrieving clinical summaries, vital signs, medications, and generating healthcare reports with HIPAA-compliant OAuth 2.0 authentication.

Category
Visit Server

README

Epic Healthcare MCP Server

A production-level Model Context Protocol (MCP) server for Epic Healthcare Systems, designed to securely integrate with Epic's FHIR R4 API and provide AI assistants with access to patient healthcare data.

🏥 Features

  • FHIR R4 Compliance: Full integration with Epic's FHIR R4 API
  • OAuth 2.0 Authentication: Secure authentication using Epic's OAuth 2.0 with JWT client assertions
  • MCP Protocol Support: Standard Model Context Protocol implementation for AI assistant integration
  • Production Ready: Comprehensive logging, error handling, and rate limiting
  • HIPAA Considerations: Designed with healthcare data security and privacy in mind
  • Scalable Architecture: Hybrid Node.js/TypeScript implementation

Available MCP Resources

  • Patient Demographics: Access to patient basic information and identifiers
  • Clinical Observations: Vital signs, lab results, and clinical measurements
  • Medications: Current and historical medication lists
  • Allergies: Patient allergy and intolerance information
  • Encounters: Healthcare visits and encounter data
  • FHIR Metadata: Server capabilities and resource definitions

Available MCP Tools

  • search_patients: Search for patients using various criteria
  • get_patient_summary: Comprehensive patient data aggregation
  • get_vital_signs: Recent vital signs and observations
  • search_observations: Query specific clinical observations

Available MCP Prompts

  • patient_summary: Generate clinical summary reports
  • clinical_assessment: Create clinical assessments from patient data

🚀 Quick Start

Prerequisites

  • Node.js 18+
  • Epic Healthcare System access
  • Epic App registration with FHIR API access
  • Valid JWT private key for Epic authentication

Installation

  1. Clone and install dependencies:
# Install MCP Server dependencies
cd mcp-server
npm install

# Install MCP Client dependencies (for testing)
cd ../mcp-client
npm install
  1. Configure environment variables:
# Copy and configure environment file
cp .env.example .env

Required environment variables:

# Epic FHIR Configuration
EPIC_CLIENT_ID=your-epic-client-id
EPIC_CLIENT_SECRET=your-epic-client-secret
EPIC_FHIR_BASE_URL=https://fhir.epic.com/interconnect-fhir-oauth/api/FHIR/R4

# JWT Authentication
JWT_PRIVATE_KEY=your-jwt-private-key
JWT_KEY_ID=your-jwt-key-id

# Server Configuration
MCP_SERVER_PORT=3000
NODE_ENV=production
LOG_LEVEL=info
  1. Build and run the server:
cd mcp-server
npm run build
npm start

Testing with MCP Client

Run the included test client to verify functionality:

cd mcp-client
npm run build
npm start

📖 Usage

Integrating with AI Assistants

The Epic Healthcare MCP Server can be integrated with AI assistants that support the Model Context Protocol:

  1. Configure the AI assistant to connect to the MCP server
  2. Use MCP resources to access patient data contextually
  3. Execute MCP tools for specific healthcare queries
  4. Leverage MCP prompts for clinical summaries and assessments

Example MCP Tool Usage

{
  "name": "search_patients",
  "arguments": {
    "name": "John Doe",
    "birthdate": "1990-01-01",
    "count": 10
  }
}
{
  "name": "get_patient_summary",
  "arguments": {
    "patientId": "patient-12345"
  }
}

🔧 Configuration

Epic FHIR Setup

  1. Register your application with Epic's developer program

  2. Configure FHIR scopes for required resource access:

    • system/Patient.read
    • system/Observation.read
    • system/Encounter.read
    • system/Medication.read
    • system/AllergyIntolerance.read
  3. Generate JWT key pair for client authentication

  4. Configure redirect URLs and authentication endpoints

Security Configuration

  • Rate Limiting: Configurable request limits to prevent API abuse
  • JWT Authentication: Secure client assertion-based authentication
  • HTTPS Only: All API communications use encrypted connections
  • Audit Logging: Comprehensive logging for security monitoring

🏗️ Architecture

Epic Healthcare MCP Server
├── mcp-server/              # Main MCP server implementation
│   ├── src/
│   │   ├── auth/            # Epic OAuth 2.0 authentication
│   │   ├── clients/         # Epic FHIR API client
│   │   ├── config/          # Environment and configuration
│   │   ├── mcp/             # MCP protocol implementation
│   │   └── utils/           # Logging and utilities
│   └── dist/                # Built JavaScript files
├── mcp-client/              # Test client for development
└── logs/                    # Application logs

Key Components

  • EpicOAuthClient: Handles Epic's OAuth 2.0 JWT authentication
  • EpicFHIRClient: Axios-based client for FHIR API interactions
  • EpicMCPServer: Core MCP protocol server implementation
  • Environment Configuration: Zod-based configuration validation
  • Winston Logging: Structured logging for production monitoring

🧪 Development

Running in Development Mode

cd mcp-server
npm run dev

Building the Project

npm run build

Type Checking

npm run type-check

Linting

npm run lint

📋 FHIR Resource Support

Resource Type Read Search Supported Operations
Patient Demographics, identifiers
Observation Vital signs, lab results
Encounter Visits, appointments
MedicationRequest Prescriptions, medications
AllergyIntolerance Allergies, intolerances
Condition Diagnoses, problems
Procedure Medical procedures

🔒 Security & Compliance

HIPAA Considerations

  • Data Minimization: Only request necessary patient data
  • Audit Trails: Comprehensive logging of all data access
  • Encryption: All data transmission uses TLS encryption
  • Access Controls: OAuth 2.0 scoped access to Epic resources

Best Practices

  • Store JWT private keys securely
  • Rotate authentication tokens regularly
  • Monitor API usage and access patterns
  • Implement proper error handling to prevent data leakage
  • Regular security audits and penetration testing

📚 API Documentation

Epic FHIR API Documentation

MCP Protocol Documentation

🐛 Troubleshooting

Common Issues

Authentication Failures

  • Verify Epic client ID and private key configuration
  • Check JWT key ID matches Epic app registration
  • Ensure proper OAuth scopes are configured

FHIR API Errors

  • Verify Epic FHIR base URL is correct
  • Check patient ID format and existence
  • Review Epic API rate limits and quotas

MCP Connection Issues

  • Verify MCP client configuration
  • Check server logs for connection errors
  • Ensure proper transport configuration

Logging

Logs are written to:

  • logs/combined.log - All application logs
  • logs/error.log - Error-level logs only
  • Console output in development mode

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make changes with proper tests
  4. Submit a pull request

📞 Support

For Epic-specific issues:

For MCP protocol issues:

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured