A Model Context Protocol (MCP) server for FalkorDB, allowing AI models to query and interact with graph databases.

This project implements a server that follows the Model Context Protocol (MCP) specification to connect AI models with FalkorDB graph databases. The server translates and routes MCP requests to FalkorDB and formats the responses according to the MCP standard.

• Node.js (v16 or later)
• npm or yarn
• FalkorDB instance (can be run locally or remotely)

1. Clone this repository:

   git clone https://github.com/falkordb/falkordb-mcpserver.git
   cd falkordb-mcpserver

2. Install dependencies:

   npm install

3. Copy the example environment file and configure it:

   cp .env.example .env

   Edit .env with your configuration details.

Configuration is managed through environment variables in the .env file:

• PORT: Server port (default: 3000)
• NODE_ENV: Environment (development, production)
• FALKORDB_HOST: FalkorDB host (default: localhost)
• FALKORDB_PORT: FalkorDB port (default: 6379)
• FALKORDB_USERNAME: Username for FalkorDB authentication (if required)
• FALKORDB_PASSWORD: Password for FalkorDB authentication (if required)
• MCP_API_KEY: API key for authenticating MCP requests

Start the development server with hot-reloading:

npm run dev

Build and start the server:

npm run build
npm start

• GET /api/mcp/metadata: Get metadata about the FalkorDB instance and available capabilities
• POST /api/mcp/context: Execute queries against FalkorDB
• GET /api/mcp/health: Check server health
• GET /api/mcp/graphs: Returns the list of Graphs

To use this server with MCP clients, you can add it to your MCP configuration:

{
  "mcpServers": {
    "falkordb": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-p", "3000:3000",
        "--env-file", ".env",
        "falkordb-mcpserver",
        "falkordb://host.docker.internal:6379"
      ]
    }
  }
}

For client-side configuration:

{
  "defaultServer": "falkordb",
  "servers": {
    "falkordb": {
      "url": "https://localhost:3000/api/mcp",
      "apiKey": "your_api_key_here"
    }
  }
}

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.