Metabase MCP Server
@cheukyin175
About Metabase MCP Server
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.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"metabase-mcp": {
"command": "uvx",
"args": [
"metabase-mcp"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Metabase MCP?
A Model Context Protocol (MCP) server that connects AI assistants like Claude, Cursor, and other MCP clients to a Metabase instance. It enables querying databases, executing SQL, managing dashboards, and automating analytics workflows through natural language. Designed for data analysts, developers, and teams integrating AI with Metabase business intelligence.
How to use Metabase MCP?
Install via uvx metabase-mcp (no installation required) or pip install metabase-mcp. Configure a .env file with Metabase credentials (API key or email/password). Run the server with uvx metabase-mcp or from source using uv run python server.py. Additional transport options: --sse for SSE, --http for HTTP.
Key features of Metabase MCP
- List databases, explore tables, and inspect fields with metadata
- Execute native SQL queries with parameter support and templating
- Execute MongoDB queries with automatic JSON conversion
- Run, create, and manage Metabase cards/questions
- Create and organize collections for better data organization
- Secure authentication via API keys or email/password
Use cases of Metabase MCP
- Let AI assistants query Metabase databases using plain English
- Automate the creation and organization of Metabase cards and collections
- Use AI for data exploration and insight discovery
- Get AI help writing and optimizing SQL queries
- Integrate AI-powered analytics into development workflows
FAQ from Metabase MCP
How does Metabase MCP authenticate with Metabase?
It supports API key authentication (recommended) or email/password authentication, configured via environment variables in a .env file.
What Python version is required?
Python 3.12+ is required.
Does it support MongoDB queries?
Yes, the server can execute native MongoDB queries with automatic JSON conversion for aggregation pipelines.
What transport methods are available?
STDIO (default for IDE integration), SSE (Server-Sent Events), and HTTP (standard HTTP for API access).
Can I run the server without installing it?
Yes, using uvx metabase-mcp runs the server directly without a permanent installation.
Frequently asked questions
How does Metabase MCP authenticate with Metabase?
It supports API key authentication (recommended) or email/password authentication, configured via environment variables in a `.env` file.
What Python version is required?
Python 3.12+ is required.
Does it support MongoDB queries?
Yes, the server can execute native MongoDB queries with automatic JSON conversion for aggregation pipelines.
What transport methods are available?
STDIO (default for IDE integration), SSE (Server-Sent Events), and HTTP (standard HTTP for API access).
Can I run the server without installing it?
Yes, using `uvx metabase-mcp` runs the server directly without a permanent installation.
Basic information
More Data & Analytics MCP servers
MCP From Zero: Quick Data
dislerPrompt focused MCP Server for .json and .csv agentic data analytics for Claude Code
mcp-simple-arxiv
andybrandtTool to work with arXiv, provide LLM with ability to search and read papers from there
dbt MCP Server
dbt-labsA MCP (Model Context Protocol) server for interacting with dbt.
PubMed Analysis MCP Server
DarkroasterA PubMed MCP server.

PowerDMARC
powerdmarcPowerDMARC's MCP server brings live email authentication data directly into any MCP-compatible AI assistant: Claude, ChatGPT, Cursor, and others. Instead of generic DMARC advice, the AI works from a customer's actual acc
Comments