Export large SQL query results or saved Metabase cards to CSV, JSON, or XLSX format. Automatically saves files to Downloads/Metabase folder, supporting up to 1 million rows of data.
Execute API calls to external platforms (Airtable, GitHub, Slack, etc.) with scoped permissions and optional human approval. Blocks until approval or returns pending status.
Moves dashboard filter widgets from the header to render inline on specific dashcards, preserving existing inline parameters unless replace is set to true.
Rearrange dashboard layout by updating positions and sizes of multiple cards in a single atomic request. Specify dashcard IDs and optionally set column, row, width, or height; omitted fields keep current values.
Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the Streamable HTTP transport and builds on Metabase's Agent API to expose tools for searching, exploring, querying, and visualizing data — all scoped to the connecting user's permissions.
A high-performance Model Context Protocol server for AI integration with Metabase analytics platforms. Features response optimization, robust error handling, and comprehensive data access tools.
Execute SQL queries or run saved Metabase cards to retrieve up to 500 rows of data from databases, with options for custom queries or predefined card filters.
Map dashboard parameters to card template tags on dashcards, linking filter values to SQL variables by specifying dashcard ID, parameter ID, and template tag. Supports dimension filters and optional full replacement of existing mappings.
Find Metabase content like cards, dashboards, tables, and collections using native search. Organize results by type and access search metrics and recommendations.
Update the parameters list on a Metabase card to control filter widgets and dashboard parameter wiring. Each parameter defines widget type, target, and defaults. Allows merge or full replacement.