metabase-mcp

metabase-mcp

3.4
databasesdeveloper_tools

If you are the rightful owner of metabase-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

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

Metabase FastMCP Server

A FastMCP (Model Context Protocol) server for Metabase, built with Python. This server provides tools to interact with Metabase databases, execute queries, manage cards, and work with collections.

Features

  • List and manage Metabase databases
  • Execute SQL queries and saved questions/cards
  • Create and manage cards (questions)
  • Work with collections
  • List tables and fields
  • Full authentication support (API Key or Session-based)

Installation

Quick Start with uv (Recommended)

  1. Install uv if not already installed: Please refer to uv

  2. Clone and setup:

uv sync  # Install dependencies and create virtual environment
  1. Configure environment:
cp .env.example .env
# Edit .env with your Metabase configuration

Alternative Installation (pip)

pip install -r requirements.txt

Configuration

Set the following environment variables in your .env file:

  • METABASE_URL: Your Metabase instance URL
  • METABASE_API_KEY: Your Metabase API key (preferred method)

OR

  • METABASE_USER_EMAIL: Your Metabase user email
  • METABASE_PASSWORD: Your Metabase password

Usage

Run the Server

# STDIO transport (default)
uv run python server.py

# SSE transport on port 8000
uv run python server.py --sse

# SSE transport on custom port
uv run python server.py --sse 9000

# HTTP transport on port 8000
uv run python server.py --http

FastMCP CLI Integration

# Run with FastMCP CLI
fastmcp run server.py

# Install as Claude Desktop MCP server
fastmcp install server.py -n "Metabase MCP"

Cursor Integration

For Cursor IDE integration:

STDIO Transport (Default)
uv run python scripts/install-cursor.py
SSE Transport
# Install with SSE transport
uv run python scripts/install-cursor.py --sse        # Port 8000 (default)
uv run python scripts/install-cursor.py --sse 9000   # Custom port

# Or use the dedicated SSE installer
uv run python scripts/install-cursor-sse.py          # Port 8000
uv run python scripts/install-cursor-sse.py 9000     # Custom port

Important for SSE: You must start the server before using Cursor:

uv run python server.py --sse 8000

Available Tools

  • list_databases: List all databases in Metabase
  • list_cards: List all questions/cards in Metabase
  • execute_card: Execute a Metabase question/card and get results
  • execute_query: Execute a SQL query against a Metabase database
  • create_card: Create a new question/card in Metabase
  • list_collections: List all collections in Metabase
  • create_collection: Create a new collection in Metabase
  • list_tables: List all tables in a database
  • get_table_fields: Get all fields/columns in a table

Transport Methods

The server supports multiple transport methods:

  • STDIO (default): For IDE integration (Cursor, Claude Desktop)
  • SSE: Server-Sent Events for web applications
  • HTTP: Standard HTTP for API access
uv run python server.py          # STDIO (default)
uv run python server.py --sse    # SSE on port 8000
uv run python server.py --http   # HTTP on port 8000

Development

Development Setup

# Install development dependencies (Python 3.12+)
uv sync --group dev

# Run tests
uv run pytest

# Format and lint code
uv run ruff check .          # Lint
uv run ruff format .         # Format
uv run black .               # Alternative formatter
uv run isort .               # Import sorting

# Type checking
uv run mypy server.py

Validation

# Validate installation
uv run python scripts/validate.py

Examples

Check out the example files for usage patterns:

  • examples/examples.py - Basic usage examples
  • examples/quick-start.py - Quick start guide
  • examples/sse-example.py - SSE transport usage example

Files Overview

  • server.py - Main FastMCP server
  • pyproject.toml - Modern Python project configuration
  • scripts/install-cursor.py - Cross-platform Cursor installation
  • scripts/install-cursor-sse.py - SSE-specific Cursor installation
  • scripts/validate.py - Installation validation
  • examples/ - Usage examples and quick start guides
  • tests/test_server.py - Basic server tests
  • config/cursor-config.json - Example Cursor configuration

Related MCP Servers

View all databases servers →
mindsdb

mindsdb

4.5

by mindsdb

MindsDB is an open-source server that enables seamless interaction with large-scale federated data using the Model Context Protocol (MCP).

databases
dbhub

dbhub

4.4

by bytebase

DBHub is a universal database gateway implementing the Model Context Protocol (MCP) server interface.

databases
notion-mcp-server

notion-mcp-server

3.7

by makenotion

This project implements an MCP server for the Notion API, allowing integration with LLMs.

databases
anyquery

anyquery

3.7

by julien040

Anyquery is a versatile SQL query engine that allows users to run SQL queries on various data sources, including files, databases, and applications, with support for LLMs and MySQL server functionality.

databases
supabase-mcp-server

supabase-mcp-server

3.7

by alexander-zuev

Query MCP is an open-source MCP server that lets your IDE safely run SQL, manage schema changes, call the Supabase Management API, and use Auth Admin SDK — all with built-in safety controls.

databases
mcp-clickhouse

mcp-clickhouse

3.7

by ClickHouse

An MCP server for ClickHouse that allows executing SQL queries and managing databases and tables.

databases
mariadb-mcp-server

mariadb-mcp-server

3.7

by rjsalgado

This MCP server provides access to MariaDB / MySQL databases, allowing users to list databases, tables, describe table schemas, and execute SQL queries with security features.

databases
mcp-server-elasticsearch

mcp-server-elasticsearch

3.7

by elastic

This server connects agents to your Elasticsearch data using the Model Context Protocol, allowing interaction with Elasticsearch indices through natural language conversations.

databases
osv-mcp

osv-mcp

3.7

by StacklokLabs

An MCP server providing access to the OSV database for querying vulnerability information.

databases
chroma-mcp

chroma-mcp

3.7

by chroma-core

Chroma MCP Server is an open-source embedding database server that facilitates the integration of LLM applications with external data sources using the Model Context Protocol.

databases
mcp-proxy

mcp-proxy

3.7

by TBXark

An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.

databases
mcp-google-sheets

mcp-google-sheets

3.6

by xing5

mcp-google-sheets is a Python-based MCP server that connects MCP-compatible clients to Google Sheets API for automation and data manipulation.

cloud_platforms
mcp-server-motherduck

mcp-server-motherduck

3.6

by motherduckdb

An MCP server implementation that interacts with DuckDB and MotherDuck databases, providing SQL analytics capabilities to AI Assistants and IDEs.

databases
atlas-mcp-server

atlas-mcp-server

3.6

by cyanheads

ATLAS (Adaptive Task & Logic Automation System) is a project, knowledge, and task management system for LLM Agents, implemented as a Model Context Protocol (MCP) server.

developer_tools
mcp-alchemy

mcp-alchemy

3.6

by runekaagaard

MCP Alchemy is a model context protocol server that connects Claude Desktop to various databases, enabling advanced database exploration and query execution.

databases
mcp-mongo-server

mcp-mongo-server

3.6

by kiliczsh

A Model Context Protocol server that enables LLMs to interact with MongoDB databases, providing capabilities for inspecting collection schemas and executing MongoDB operations through a standardized interface.

databases
mcp-server-splunk

mcp-server-splunk

3.6

by jkosik

A Go implementation of the MCP server for Splunk, supporting STDIO and SSE (Server-Sent Events HTTP API) using the github.com/mark3labs/mcp-go SDK.

cloud_platforms
mcp-redis

mcp-redis

3.6

by redis

The Redis MCP Server is a natural language interface designed for agentic applications to efficiently manage and search data in Redis.

databases
mssql_mcp_server

mssql_mcp_server

3.6

by RichardHan

A Model Context Protocol (MCP) server that enables secure interaction with Microsoft SQL Server databases.

databases
firebase-mcp

firebase-mcp

3.6

by gannonh

Firebase MCP enables AI assistants to work directly with Firebase services, including Firestore, Storage, and Authentication.

databases
elasticsearch-mcp-server

elasticsearch-mcp-server

3.6

by cr7258

A Model Context Protocol (MCP) server implementation that provides Elasticsearch and OpenSearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools.

databases
supabase-mcp

supabase-mcp

3.6

by coleam00

A Model Context Protocol (MCP) server that provides tools for interacting with a Supabase database. This server enables AI assistants to perform database operations through a standardized interface.

databases
postgres-mcp-server

postgres-mcp-server

3.6

by aadarshjain

A Model Context Protocol (MCP) server implementation for PostgreSQL database exploration and querying.

databases
meilisearch-mcp

meilisearch-mcp

3.6

by meilisearch

A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces like Claude.

databases
mcp-server-bigquery

mcp-server-bigquery

3.6

by LucasHild

A Model Context Protocol server that provides access to BigQuery, enabling LLMs to inspect database schemas and execute queries.

databases
MCPServerForMSSQL

MCPServerForMSSQL

3.6

by shakunvohradeltek

This repository contains the SQL Server MCP (Model Context Protocol) integration for Claude, allowing direct querying and analysis of SQL Server databases using natural language.

databases
doris-mcp-server

doris-mcp-server

3.6

by apache

Doris MCP Server is a backend service built with Python and FastAPI, designed to connect to Apache Doris databases and potentially leverage LLMs for tasks like NL2SQL.

databases