Frequently Asked Questions (FAQ)

Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs (Large Language Models). An MCP server acts as a bridge, allowing AI models to access and interact with external data sources and tools, such as Metabase.

Q: What is the Metabase MCP Server? A: The Metabase MCP Server provides integration with the Metabase API, enabling LLMs to directly interact with your analytics data. It acts as a bridge between your analytics platform and conversational AI.

Q: What are the key features of the Metabase MCP Server? A: Key features include resource access via metabase:// URIs, support for session-based and API key authentication, JSON-formatted responses, comprehensive logging, and robust error handling.

Q: What tools are available for AI assistants through the Metabase MCP Server? A: Available tools include data access tools (e.g., list_dashboards, list_tables), execution tools (e.g., execute_card, execute_query), and dashboard/collection management tools (e.g., create_dashboard, create_collection).

Q: How do I install the Metabase MCP Server? A: The server requires Node.js 18.0.0 or higher and an active Metabase instance. You can install dependencies using npm install, build the project with npm run build, and start the server with npm start. Refer to the documentation for detailed instructions, including Claude Desktop integration.

Q: What are the authentication options for the Metabase MCP Server? A: The server supports two authentication methods: username and password authentication, and API key authentication (recommended for production).

Q: How can I debug the Metabase MCP Server? A: You can use the MCP Inspector for debugging, which provides a browser-based interface for monitoring requests and responses. Run npm run inspector to start the Inspector.

Q: Is Docker supported? A: Yes, a Docker image is available for containerized deployment. You can build the image using docker build -t metabase-mcp . and run the container with appropriate environment variables.

Q: What security considerations should I keep in mind? A: It’s recommended to use API key authentication for production, keep your API keys and credentials secure, and apply appropriate network security measures to restrict access to your Metabase instance.

Q: Where can I find the UBOS Asset Marketplace? A: The UBOS Asset Marketplace is integrated within the UBOS platform. Contact UBOS support or sales for access and details.

Q: How does the Metabase MCP server relate to UBOS? A: UBOS is a full-stack AI Agent Development Platform. The Metabase MCP server is an asset in the UBOS Asset Marketplace that allows you to connect AI Agents with your Metabase data.

Q: What are the prerequisites for using the Metabase MCP Server? A: You will need an active Metabase instance with appropriate credentials, Node.js 18.0.0 or higher for local development, and access to the UBOS platform if you intend to deploy it through UBOS.