Metabase MCP server

This MCP server enables AI assistants to interact with Metabase, providing access to dashboards, questions/cards, and databases. It allows for executing queries and interacting with Metabase data through a standardized protocol interface.

Installation

Prerequisites

Before installing the server, ensure you have:

• Node.js installed
• Access credentials to your Metabase instance

Basic Installation

To install the Metabase MCP server:

npm install @imlewc/metabase-server

Quick Installation via Smithery

For an automated setup with Claude Desktop:

npx -y @smithery/cli install @imlewc/metabase-server --client claude

Configuration

The server requires the following environment variables:

# Required environment variables
export METABASE_URL=https://your-metabase-instance.com
export METABASE_USERNAME=your_username
export METABASE_PASSWORD=your_password

Claude Desktop Configuration

To configure the server with Claude Desktop, edit the configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration:

{
  "mcpServers": {
    "metabase-server": {
      "command": "/path/to/metabase-server/build/index.js",
      "env": {
        "METABASE_URL": "https://your-metabase-instance.com",
        "METABASE_USERNAME": "your_username",
        "METABASE_PASSWORD": "your_password"
      }
    }
  }
}

You can alternatively set these environment variables at the system level rather than in the config file.

Using the Server

Available Resources

Access Metabase resources using the metabase:// URI scheme:

• Dashboards
• Cards/questions
• Databases

Available Tools

The server provides several tools for interacting with Metabase:

• list_dashboards - Get all dashboards in your Metabase instance
• list_cards - Get all questions/cards
• list_databases - Get all databases
• execute_card - Run a Metabase question/card and retrieve results
• get_dashboard_cards - Retrieve all cards in a specific dashboard
• execute_query - Run SQL queries against Metabase databases

Example: Listing Dashboards

To list all dashboards in your Metabase instance:

// Use the list_dashboards tool in your AI assistant

Example: Executing a Query

To run a specific card/question:

// Use the execute_card tool with the card ID

Example: Working with SQL

To execute a custom SQL query:

// Use the execute_query tool with your SQL and database ID

Troubleshooting

If you encounter issues with the server, you can use the MCP Inspector for debugging:

npm run inspector

This will provide a URL to access debugging tools in your browser, which can help diagnose communication issues between the AI assistant and the Metabase instance.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.