metabase-mcp

metabase-mcp

3.4

If you are the rightful owner of metabase-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A Model Context Protocol server that integrates AI assistants with Metabase analytics platform.

The Metabase MCP Server is designed to seamlessly integrate AI assistants with the Metabase analytics platform. By leveraging the Metabase API, this server enables LLMs with MCP capabilities to interact directly with analytics data. It acts as a bridge between the analytics platform and conversational AI, allowing for intuitive data navigation and execution of queries. The server supports both session-based and API key authentication, ensuring secure access to resources. It provides JSON-formatted responses, making it easy for AI assistants to consume and process data. Additionally, the server includes comprehensive logging and robust error handling to facilitate debugging and monitoring.

Features

  • Resource Access: Navigate Metabase resources via intuitive `metabase://` URIs.
  • Two Authentication Methods: Support for both session-based and API key authentication.
  • Structured Data Access: JSON-formatted responses for easy consumption by AI assistants.
  • Comprehensive Logging: Detailed logging for easy debugging and monitoring.
  • Error Handling: Robust error handling with clear error messages.

Tools

  1. list_cards

    Get all saved questions/cards in Metabase.

  2. list_databases

    View all connected database sources.

  3. list_collections

    List all collections in Metabase.

  4. list_tables

    List all tables in a specific database.

  5. get_table_fields

    Get all fields/columns in a specific table.

  6. execute_card

    Run saved questions and retrieve results with optional parameters.

  7. execute_query

    Execute custom SQL queries against any connected database.

  8. create_card

    Create a new question/card with SQL query, optionally adding it to a collection.

  9. create_collection

    Create a new collection to organize dashboards and questions.