Metabase MCP server for AI agents

The Metabase MCP server enables AI assistants to interact with Metabase, providing access to dashboards, questions, databases, and query execution. It serves as a bridge between AI tools like Claude and your Metabase instance, allowing for data analysis through natural language requests.

Prerequisites

Before installation, ensure you have:

Node.js installed
Access credentials to a Metabase instance
Claude Desktop installed (if using with Claude)

Installation

Standard Installation

Clone the repository:

git clone https://github.com/imlewc/metabase-server.git
cd metabase-server

Install dependencies:
```
npm install
```
Build the server:
```
npm run build
```

Quick Installation via Smithery

For a simplified installation process with Claude Desktop:

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

Configuration

Before using the server, you must configure your Metabase credentials:

Environment Variables

Set the following 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 use with Claude Desktop, add the server config:

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

Windows: Edit %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"
      }
    }
  }
}

Usage

Available Resources

The server provides access to Metabase resources via metabase:// URIs:

Dashboards
Cards/questions
Databases

Tools

The following tools are available for interaction with Metabase:

Listing Resources

List dashboards: Use this to view all available dashboards in your Metabase instance.
List cards: Shows all available questions/cards that have been created in Metabase.
List databases: Displays all connected databases in your Metabase instance.

Working with Data

Execute card: Run a specific Metabase question/card and retrieve the results.
Get dashboard cards: Retrieve all cards contained within a specific dashboard.
Execute query: Run a custom SQL query against a Metabase database.

Debugging

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

npm run inspector

This will provide a URL to access debugging tools in your browser, which is helpful since MCP servers communicate over stdio.

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.