mcpField
M
Metabase MCP Server

Metabase MCP Server

Local
github.com/cuenca-mxData & Analytics5Updated 71w ago

About Metabase MCP Server

Metabase MCP Server exposes Metabase API browsing and query functions to AI clients. It supports cards, databases, collections, and bookmarks, as well as card and arbitrary queries.

Key features

  1. 01List Metabase cards
  2. 02View available databases
  3. 03Run card queries
  4. 04Run arbitrary queries
  5. 05Create cards and bookmarks
  6. 06List collections

Use cases

  1. 01Browse Metabase cards through an AI client
  2. 02Query databases or run card queries
  3. 03Create analysis cards and bookmarks
  4. 04Inspect Metabase collections

MCP support

The MCP server makes Metabase API operations for cards, databases, queries, bookmarks, and collections available as tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Metabase MCP Server

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

Features

  • 🔍 List Metabase cards
  • 🗄️ List available databases
  • 📊 Execute queries on cards
  • 🧾 Run arbitrary queries
  • 📝 Create new cards
  • 🔖 Create bookmark
  • 📁 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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.