Agent Skills

Metabase

Interact with Metabase, the open-source business intelligence platform, using Large Language Models.

Install

Install and configure the MCP from https://github.com/cuenca-mx/metabase-mcp-server now. Follow the repository's installation instructions, ask me for anything you can't complete yourself, and verify its tools load.
README

Metabase MCP Server

This project implements an MCP server to interact with the Metabase API, exposing key functionality via a MCP interface.

Features

  • ๐Ÿ” List Metabase cards
  • ๐Ÿ—„๏ธ List available databases
  • ๐Ÿ“Š Execute queries on cards
  • ๐Ÿงพ Run arbitrary queries
  • ๐Ÿ“ Create new cards
  • ๐Ÿ”– Create bookmark
  • ๐Ÿ“ List collections

Requirements

  • Python 3.12+
  • uv

Installation

  1. Clone the repository:
git clone https://github.com/cuenca-mx/metabase-mcp-server.git
cd metabase-mcp-server
  1. Configure your AI assistant client (Claude, Cursor, etc.) by adding the following configuration:
{
    "mcpServers": {
        "metabase": {
            "command": "uv",
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/PARENT/FOLDER/metabase_mcp_server",
                "run",
                "app.py"
            ],
            "env": {
                "METABASE_URL": "https://metabase.domain.com/",
                "METABASE_API_KEY": "your-secret-api-key"
            }
        }
    }
}

Development Setup

This project uses a Makefile to simplify development tasks:

make install

Environment Variables

Configure required environment variables:

export $(<env.template)

Running Tests

The project uses pytest for unit testing:

uv run pytest

Debugging with MCP Inspector

Use the MCP Inspector for testing and debugging:

make dev

Search skills and MCP servers

Search across 31,816 skills and MCPs