# langcare-mcp-fhir

Connects AI coding assistants directly to EMR backends using the FHIR R4 standard. Useful for reading patient charts or creating observations in clinical databases.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 67
- Author: langcare
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/langcare/langcare-mcp-fhir
- Updated: 2026-04-14
- HTML: https://affpapa.org/en/nevibecode/mcp/langcare-mcp-fhir

## What it does

This Go-powered proxy links MCP clients to healthcare systems such as Epic, Cerner, OpenEMR, or GCP Healthcare API. It runs entirely stateless without an internal database. Incoming agent calls translate directly into standard FHIR queries.

The server provides four core tools: `fhir_read`, `fhir_search`, `fhir_create`, and `fhir_update`. These generic actions handle any resource type, from `Patient` records to clinical `Observation` entries. Security handles TLS 1.3 transport, automated PHI scrubbing in logs, and SMART on FHIR authorization using RS384 signatures.

Without a valid YAML configuration pointing to your EMR endpoint, the server will fail to route requests. Store all authentication secrets in environment variables rather than configuration files.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add langcare-mcp-fhir -- npx -y @langcare/langcare-mcp-fhir
```

### Codex

**Platform CLI**
```bash
codex mcp add langcare-mcp-fhir -- npx -y @langcare/langcare-mcp-fhir
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "langcare-mcp-fhir": {
            "command": "npx",
            "args": [
                "-y",
                "@langcare/langcare-mcp-fhir"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "langcare-mcp-fhir": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@langcare/langcare-mcp-fhir"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add langcare-mcp-fhir npx -y @langcare/langcare-mcp-fhir
```

## When to use it
- query patient entries by demographic criteria using `fhir_search`
- retrieve specific clinical records via `fhir_read` by resource ID
- push new observation data into an EMR through `fhir_create`
- modify existing patient attributes using `fhir_update`

## Example prompts
- Search for patients named Smith born after 1990-01-01
- Read the FHIR observation resource with ID example-123
- Create a new final Observation entry linked to Patient/123

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409
- [OpenWork MCP Gateway](https://affpapa.org/en/nevibecode/mcp/openwork-mcp-gateway.md) — MCP server · ★ 24242
- [Keploy](https://affpapa.org/en/nevibecode/mcp/keploy.md) — MCP server · ★ 18727
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [basebalance.cloud — x402 RPC & MCP gateway](https://affpapa.org/en/nevibecode/mcp/basebalancecloud-x402-rpc-mcp-gateway.md) — MCP server · ★ 7506

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md