Metabase MCP Server
@hyeongjun-dev
A Model Context Protocol server that integrates AI assistants with Metabase analytics platform
Overview
What is Metabase MCP Server?
A Model Context Protocol server that integrates AI assistants with the Metabase analytics platform via its API. It enables conversational AI assistants like Claude to navigate Metabase resources and execute queries against dashboards, cards, and databases.
How to use Metabase MCP Server?
Install dependencies (Node.js 18.0.0+), build (npm run build), and start (npm start). Configure via environment variables: set METABASE_URL and either METABASE_USER_EMAIL/METABASE_PASSWORD (session auth) or METABASE_API_KEY (API key auth). Integrate with Claude Desktop by adding a server entry in claude_desktop_config.json. A Docker image is also available for containerized deployment.
Key features of Metabase MCP Server
- Navigate Metabase resources via
metabase://URIs. - Support for both session-based and API key authentication.
- JSON-formatted responses for AI assistant consumption.
- Configurable logging (debug, info, warn, error, fatal).
- Six tools for interacting with Metabase data.
- Robust error handling with clear error messages.
Use cases of Metabase MCP Server
- Ask an AI assistant to list all available dashboards.
- Retrieve query results from saved questions with parameters.
- Execute custom SQL queries against connected databases.
- Extract all cards from a specific dashboard.
- View all connected database sources.
FAQ from Metabase MCP Server
What authentication method is recommended for production?
API key authentication is recommended for production environments.
What log levels does the server support?
Log levels include debug, info, warn, error, and fatal.
