Metabase MCP Server

🚀 Metabase MCP Server

A Model Context Protocol (MCP) server that integrates AI assistants with the Metabase analytics platform.

🚀 Quick Start

The Metabase MCP Server is a TypeScript - based server that integrates with the Metabase API, enabling AI assistants to directly interact with your analytics data. Designed for Claude and other MCP - supported AI assistants, it serves as a bridge between the analytics platform and conversational AI.

✨ Features

• Resource Access: Navigate Metabase resources using intuitive metabase:// URIs.
• Dual Authentication Methods: Supports both session - based and API Key - based authentication.
• Structured Data Access: Responds in JSON format for easy consumption by AI assistants.
• Detailed Logging: Provides detailed logging for debugging and monitoring.
• Error Handling: Robust error handling with clear error messages.

📦 Tools Available

The server exposes the following tools for AI assistants:

• list_dashboards: Retrieve all available dashboards in a Metabase instance.
• list_cards: Get all saved questions/cards in Metabase.
• list_databases: View all connected database sources.
• execute_card: Execute a saved question and retrieve results, with optional parameters.
• get_dashboard_cards: Extract all cards from a specific dashboard.
• execute_query: Execute a custom SQL query on any connected database.

📚 Configuration

The server supports two authentication methods:

Option 1: Username and Password Authentication

# Required configuration
METABASE_URL=https://your-metabase-instance.com
METABASE_USER_EMAIL=your_email@example.com
METABASE_PASSWORD=your_password

# Optional configuration
LOG_LEVEL=info # Options: debug, info, warn, error, fatal

Option 2: API Key Authentication

# Required configuration
METABASE_URL=https://your-metabase-instance.com
METABASE_API_KEY=your_api_key_here

📦 Installation

Install using npm:

npm install metabase-mcp-server

💻 Usage Examples

Basic Usage

Start the server:

node index.js

Advanced Usage

Here is an example of a configuration file:

const config = {
  metabaseUrl: 'https://your-metabase-instance.com',
  apiKey: 'your_api_key_here',
  logLevel: 'info'
};

// Initialize the server
new MetabaseMCPServer(config);

📚 Documentation

The following environment variables are read:

🔧 Technical Details

Since the MCP server communicates via standard input and output, you can use the MCP Inspector for debugging:

npm run inspector

The inspector provides a browser - based interface to monitor requests and responses.

📦 Docker Support

A Docker image is provided for containerized deployment:

Build the image:

docker build -t metabase-mcp-server .

Run the container:

docker run -e METABASE_URL=https://your-metabase.com \
           -e METABASE_API_KEY=your_api_key \
           metabase-mcp-server

⚠️ Important Note

• It is recommended to use API Key authentication in a production environment.
• Keep your API Key and credentials secure.
• Consider using Docker secrets or environment variables instead of hard - coding credentials.
• Apply appropriate network security measures to restrict access to your Metabase instance.

🤝 Contribution

Contributions are welcome! Please feel free to submit a Pull Request.

Author: Hyeongjun Yu (@hyeongjun-dev)