LangCare MCP FHIR Server is an enterprise-grade server designed for FHIR-based electronic medical records (EMRs), enabling AI agents to interact with any FHIR R4 resource type. It provides generic FHIR operations and supports various EMR systems.
From the registry: An MCP FHIR server written in Go for EMR systems like Epic and Cerner

$ npm install -g @langcare/langcare-mcp-fhirPlease install the `langcare-mcp-fhir` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install langcare-mcp-fhir** — Install globally via npm (or use npx) Run: `npm install -g @langcare/langcare-mcp-fhir`
- **Create YAML config file** — Choose a config template for your FHIR backend (EPIC, Cerner, OpenEMR, GCP, or generic FHIR R4) (https://github.com/langcare/langcare-mcp-fhir/tree/main/configs)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@langcare/langcare-mcp-fhir","-config","/path/to/your/config.yaml"]
Note: Also supports Streamable HTTP transport with remote deployment (Fly.io). Go-based server; stdio used with npx wrapper. Provider-specific env vars (EPIC_BASE_URL, EPIC_CLIENT_ID, etc.) may be set in the YAML config or as env vars.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.API_KEYrequiredBearer Token for MCP Client Authentication.FHIR_BACKEND_AUTHrequiredAuthentication for FHIR Backend (Bearer/OAuth2).MCP server for searching Airweave collections with natural language queries.