Agent Care MCP Server - Azalea Health Integration
About
Agent Care MCP Server configured for Azalea Health FHIR API integration
Details
- Author
- vlcosent
- Downloads
- 292
- Categories
- AI
Jump to
- Connects to Azalea Health Ambulatory FHIR API
- Sandbox testing with provided credentials
- OAuth integration with client ID 290
- Supports Claude Desktop interaction
- Includes startup scripts for multiple OS
- Testable via MCP inspector
Clone the repository, install dependencies with npm install, build with npm run build, and start the server using ./start-azalea.sh (Linux/Mac) or start-azalea.bat (Windows). Configure Claude Desktop by copying claude_desktop_config.json to the appropriate OS path. Test using the MCP inspector.
Agent Care MCP Server - Azalea Health Integration
This repository contains the configuration for connecting the Agent Care MCP server to Azalea Health's Ambulatory FHIR API.
Prerequisites
- Node.js v14 or later
- npm
- Claude Desktop (for AI interaction)
Setup Instructions
1. Clone this repository:
git clone https://github.com/vlcosent/agentcare-mcp-azalea.git
cd agentcare-mcp-azalea
2. Install dependencies:
npm install
3. Build the project:
npm run build
4. Start the MCP server:
- On Linux/Mac: ./start-azalea.sh
- On Windows: start-azalea.bat
Claude Desktop Configuration
Copy the claude_desktop_config.json file to:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json
Testing
You can test the MCP server using the MCP inspector:
npm install -g @modelcontextprotocol/inspector
mcp-inspector build/index.js http://localhost:5173
Azalea Health FHIR API Configuration
The server is configured to connect to Azalea Health's Ambulatory Sandbox FHIR API with the following credentials:
- Client ID: 290
- Redirect URI: http://localhost:3456/oauth/callback
- Base FHIR URL: https://app.azaleahealth.com/fhir/R4/sandbox
These credentials are for sandbox testing only and do not provide access to real patient data.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
