Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Medikode Medical Coding MCP Server validate these codes for this patient chart: 99213, I10, E11.9"
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.
Bring AI-powered medical coding into Claude, Cursor, and ChatGPT.
The Medikode MCP Server exposes Medikode.ai's medical coding platform through the Model Context Protocol. Coders, auditors, and revenue cycle teams can validate codes, QA charts, parse EOBs, and score risk adjustment directly from the AI assistant they already use — with every call authenticated, tracked, and billed through their Medikode account.
Revenue cycle teams spend hours moving between EHRs, coding tools, and payer portals. LLM assistants are good at reading clinical notes but have no reliable source of truth for code validity, NCCI edits, or RAF weights. This server closes that gap: the assistant does the reasoning, and Medikode's platform supplies the validated, auditable answer.
Related MCP server: OMOPHub MCP Server
Tool | What it does | Typical use |
| Checks CPT / ICD-10 codes against the clinical documentation | Pre-bill validation |
| Runs a coding quality-assurance review on a chart | Audit and coder feedback |
| Extracts structured data from insurance EOBs / remittances | Payment posting, denial analysis |
| Calculates Risk Adjustment Factor (RAF) scores | Risk adjustment / HCC workflows |
| Combines code validation and RAF scoring in one call | End-to-end chart review |
Requirements: Node.js 24.7+ and a Medikode API key (get one at medikode.ai).
npm install -g @medikode/mcp-serverAdd to claude_desktop_config.json:
{
"mcpServers": {
"medikode": {
"command": "npx",
"args": ["-y", "@medikode/mcp-server"],
"env": {
"MEDIKODE_API_KEY": "your-api-key"
}
}
}
}Add the same block to Cursor's MCP settings (~/.cursor/mcp.json).
Restart the client, then ask something like:
"Validate CPT 99214 with ICD-10 E11.9 against this note…"
AI assistant (Claude / Cursor / ChatGPT)
│ MCP (stdio or WebSocket)
▼
Medikode MCP Server ── API key auth · caching · request validation (Joi)
│ HTTPS
▼
Medikode API ── prod / sandbox routing
│
▼
Coding engine · NCCI edits · RAF models · usage dashboardTransports: stdio for desktop clients; WebSocket for hosted and ChatGPT integrations
Environment routing: separate production and sandbox API endpoints
Security: API-key authentication, Helmet, configurable CORS, no PHI stored by the server
Observability: health checks, structured logging, and per-call usage in the Medikode dashboard
Copy env.example to .env:
Variable | Purpose |
| Server port (default |
|
|
| Production Medikode API |
| Sandbox Medikode API |
| Backend service URL |
| CORS allow-list |
| Logging verbosity |
| Health-check timeout (ms) |
Docker:
docker compose up -dgit clone https://github.com/raelango/medikode-mcp-server.git
cd medikode-mcp-server
npm install
npm run devTests cover unit behaviour, environment routing, WebSocket transport, MCP Inspector compatibility, and ChatGPT integration (test-*.js, test-chatgpt-integration.py).
See CONTRIBUTING.md and CHANGELOG.md.
medikode-agents — pipeline stage definitions and Claude Code skills for Medikode's coding, audit, ERA, RAF, and validation agents
ISC © Medikode.ai
This server cannot be deployed
Your MedNode health vault in your AI assistant — records, summaries, labs, appointments.
ICD-10-CM / HCC medical coding tools with database-verified accuracy and denial-prevention rules.
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
Let AI agents query data and act across all your business apps via MCP.
