Metabase

Metabase MCP server provides integration with the Metabase API, enabling LLM with MCP capabilites to directly interact with your analytics data, this server acts as a bridge between your analytics platform and conversational AI.

javascript

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "blekzz-metabase-mcp-zsh52013148087": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "YOUR_GITHUB_USERNAME/metabase-mcp-server",
        "--config",
        "{\"metabaseUrl\":\"https://your-metabase-instance.com\",\"metabaseApiKey\":\"your_api_key\",\"metabasePassword\":\"\",\"metabaseUserEmail\":\"\"}"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "METABASE_URL": "https://your-metabase-instance.com",
        "METABASE_API_KEY": "your_api_key",
        "METABASE_PASSWORD": "your_password",
        "METABASE_USER_EMAIL": "user@example.com"
      }
    }
  }
}

This MCP server bridges Metabase analytics with conversational AI, enabling AI assistants to access dashboards, charts, databases, and run questions directly against your Metabase instance. You’ll be able to navigate resources, execute saved questions, and manage dashboards through natural language workflows.

How to use

You will interact with Metabase data through a client that speaks the MCP protocol. Use data access tools to discover dashboards, cards, databases, and tables. Use execution tools to run saved questions or custom SQL queries. Use dashboard and card management to compose, organize, and visualize analytics for AI-assisted workflows.

How to install

Prerequisites you need before starting include Node.js and npm, along with a GitHub account if you plan to deploy via Smithery. Ensure you have access to your Metabase instance and the necessary credentials (API key or user/password). Create a target Metabase URL such as https://your-metabase-instance.com.

Step 1: Clone the MCP server repository to your workspace.

Step 2: Install dependencies.

Step 3: Start the MCP server using one of the supported deployment methods shown below.

Security considerations

Prefer API key authentication for production deployments. Keep all credentials secure and avoid hardcoding them in scripts. Consider using environment variables and restrict network access to your Metabase instance.

Notes on deployment and configuration

To run this MCP server with Claude or other AI assistants, you can deploy via Smithery. The deployment configuration is provided as executable commands that you run in your environment.

Troubleshooting and tips

If you encounter authentication or connection issues, verify that the Metabase URL is accurate, and that you are using the correct authentication method (API key or email/password). Check environment variables align with the chosen method and that the MCP runtime has access to the network where Metabase resides.

Available tools

list_dashboards

Retrieve all dashboards in your Metabase instance to understand available analytics surfaces.

list_cards

Fetch all saved questions or cards stored in Metabase for quick reuse.

list_databases

Show all connected database sources so you can query across data stores.

list_collections

List all collections to organize dashboards and questions.

list_tables

List all tables in a given database to discover schema.

get_table_fields

Get all fields/columns for a specific table to inform queries.

execute_card

Run a saved question/card and retrieve results, with optional parameters.

execute_query

Execute a custom SQL query against any connected database.

get_dashboard_cards

Extract all cards from a specific dashboard for consolidation.

create_dashboard

Create a new dashboard with a name and configuration parameters.

update_dashboard

Update an existing dashboard’s name, description, or parameters.

delete_dashboard

Delete a dashboard that is no longer needed.

add_card_to_dashboard

Add or update cards in a dashboard with position and tab options.

create_card

Create a new card or question with an associated SQL query.

update_card_visualization

Modify visualization settings for a card to adjust presentation.

create_collection

Create a new collection to organize dashboards and questions.

Built by

VeilStrat

AI signals for GTM teams