Metabase MCP Server is a Model Context Protocol integration that connects AI assistants to Metabase analytics platforms. It enables conversational access to dashboards, saved questions, and database queries through structured JSON responses. Key features: - Browse and retrieve all available dashboards and saved questions/cards from your Metabase instance - Execute custom SQL queries against any connected database source - Run saved questions with optional parameters and extract results - Support for both session-based (username/password) and API key authentication - Navigate Metabase resources via intuitive `metabase://` URIs - Comprehensive logging and robust error handling for debugging and monitoring

Metabase MCP Server

Author: Hyeongjun Yu (@hyeongjun-dev)

[](https://smithery.ai/server/@hyeongjun-dev/metabase-mcp-server)

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

Overview

This TypeScript-based MCP server provides seamless integration with the Metabase API, enabling AI assistants to directly interact with your analytics data. Designed for Claude and other MCP-compatible AI assistants, this server acts as a bridge between your analytics platform and conversational AI.

Key Features

Available Tools

The server exposes the following tools for AI assistants:

Configuration

The server supports two authentication methods:

Option 1: Username and Password Authentication

# Required
METABASE_URL=https://your-metabase-instance.com
METABASE_USER_EMAIL=your_email@example.com
METABASE_PASSWORD=your_password
Optional
LOG_LEVEL=info # Options: debug, info, warn, error, fatal

Option 2: API Key Authentication (Recommended for Production)

# Required
METABASE_URL=https://your-metabase-instance.com
METABASE_API_KEY=your_api_key
Optional
LOG_LEVEL=info # Options: debug, info, warn, error, fatal

You can set these environment variables directly or use a .env file with dotenv.

Installation

Prerequisites

Development Setup

# Install dependencies
npm install
Build the project
npm run build
Start the server
npm start
For development with auto-rebuild
npm run watch

Claude Desktop Integration

To use with Claude Desktop, add this server configuration:

MacOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: Edit %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "metabase-mcp-server": {
      "command": "/absolute/path/to/metabase-mcp-server/build/index.js",
      "env": {
        "METABASE_URL": "https://your-metabase-instance.com",
        "METABASE_USER_EMAIL": "your_email@example.com",
        "METABASE_PASSWORD": "your_password"
        // Or alternatively, use API key authentication
        // "METABASE_API_KEY": "your_api_key"
      }
    }
  }
}

Alternatively, you can use the Smithery hosted version via npx with JSON configuration:

#### API Key Authentication:

{
  "mcpServers": {
    "metabase-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@hyeongjun-dev/metabase-mcp-server",
        "--config",
        "{\"metabaseUrl\":\"https://your-metabase-instance.com\",\"metabaseApiKey\":\"your_api_key\",\"metabasePassword\":\"\",\"metabaseUserEmail\":\"\"}"
      ]
    }
  }
}

#### Username and Password Authentication:

{
  "mcpServers": {
    "metabase-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "@hyeongjun-dev/metabase-mcp-server",
        "--config",
        "{\"metabaseUrl\":\"https://your-metabase-instance.com\",\"metabaseApiKey\":\"\",\"metabasePassword\":\"your_password\",\"metabaseUserEmail\":\"your_email@example.com\"}"
      ]
    }
  }
}

Debugging

Since MCP servers communicate over stdio, use the MCP Inspector for debugging:

npm run inspector

The Inspector will provide a browser-based interface for monitoring requests and responses.

Docker Support

A Docker image is available for containerized deployment:

# Build the Docker image
docker build -t metabase-mcp-server .
Run the container with environment variables
docker run -e METABASE_URL=https://your-metabase.com \
           -e METABASE_API_KEY=your_api_key \
           metabase-mcp-server

Security Considerations