A high-performance Model Context Protocol (MCP) server for Metabase, enabling AI assistants like Claude, Cursor, and other MCP clients to interact seamlessly with your Metabase instance. Query…
Metabase MCP Server is an MCP project maintained in the cheukyin175/metabase-mcp repository. The maintainer describes its purpose as “A high-performance Model Context Protocol (MCP) server for Metabase, enabling AI assistants like Claude, Cursor, and other MCP clients to interact seamlessly with your Metabase…”. Read the project documentation for the complete scope.
The documented pypi package is metabase-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares METABASE_URL, METABASE_API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| list_databases | List all configured databases in Metabase |
| list_tables | Get all tables in a specific database with metadata |
| get_table_fields | Retrieve field/column information for a table |
| execute_query | Execute native SQL queries with parameter support |
| execute_mongodb_query | Execute native MongoDB queries with automatic JSON conversion for aggregation pipelines |
| execute_card | Run saved Metabase questions/cards |
| list_cards | List all saved questions/cards |
| create_card | Create new questions/cards with SQL queries |
| create_mongodb_card | Create new MongoDB questions/cards with native query support |
| list_collections | Browse all collections |
| create_collection | Create new collections for organization |
{
"mcpServers": {
"metabase-mcp": {
"command": "uvx",
"args": [
"metabase-mcp"
],
"env": {
"METABASE_URL": "https://your-metabase-instance.com",
"METABASE_API_KEY": "YOUR_METABASE_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| METABASE_URL | Declared in the maintainer’s client configuration. | Check documentation |
| METABASE_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Facilitates interaction with the PyTorch HUD API, providing access to CI/CD data, job logs, and analytics.
MCP server for 1C:Enterprise (1С) over OData. Ask your accounting database in natural language — debtors, sales, taxes, cash flow — from any MCP
Your AI marketing analyst, connected to live data. 75 MCP tools across Google Ads, Meta Ads, GA4, Search Console, Shopify, Stripe and WordPress — read, analyze, manage, and monitor.
Draft, schedule and publish LinkedIn posts, reply to comments and read analytics via 2pr.io.
Read Accredible credentials, groups, designs, analytics, skills; issue one credential as a draft.