metabase-mcp
Provides tools for querying and managing a Metabase instance, enabling AI agents to execute queries, explore schemas, and build dashboards.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@metabase-mcpshow me all tables in the sample database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Metabase MCP Server
Complietly vibecoded a TypeScript/Node.js MCP (Model Context Protocol) server that wraps the Metabase REST API, giving AI agents (Claude Desktop, Claude Code) full programmatic access to a Metabase v0.59.x instance. Agents can execute queries, explore schemas, and build dashboards entirely through structured tool calls — no human click-through required.
Prerequisites
Node.js 20 LTS or later
Docker (for running a local Metabase instance during development)
A Metabase instance reachable over HTTP/HTTPS with an API key
Related MCP server: Gel Database MCP Server
Setup
Install dependencies:
npm installBuild the server:
npm run buildCompiled output is written to
dist/. The entry point isdist/index.js.Configure environment variables (copy
.env.exampleand fill in values):cp .env.example .env(Optional) Start a local Metabase instance for development:
docker compose up -dMetabase is available at
http://localhost:3000once healthy (allow ~2 minutes on first boot).
Environment Variables
Variable | Required | Description |
| Yes | Base URL of your Metabase instance, e.g. |
| Yes | API key created in Admin → Settings → Authentication → API Keys |
API Key Permissions: The API key must belong to a Metabase group with sufficient permissions for the operations you need. For full agent access (read schema, execute queries, create/edit cards and dashboards), the key's group should have access to all relevant databases and admin capabilities. A key with only basic viewer permissions will return 403 errors on write operations.
Adding to Claude Desktop
Add the following to your Claude Desktop MCP config file (typically ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"metabase": {
"command": "node",
"args": ["/absolute/path/to/metabase-mcp/dist/index.js"],
"env": {
"METABASE_URL": "http://localhost:3000",
"METABASE_API_KEY": "your-api-key-here"
}
}
}
}Replace /absolute/path/to/metabase-mcp with the actual path to this project.
Adding to Claude Code
Add the same config to your Claude Code MCP settings:
{
"mcpServers": {
"metabase": {
"command": "node",
"args": ["/absolute/path/to/metabase-mcp/dist/index.js"],
"env": {
"METABASE_URL": "http://localhost:3000",
"METABASE_API_KEY": "your-api-key-here"
}
}
}
}Verifying the Connection
Once added to Claude Desktop or Claude Code, ask the agent to call the server_ping tool:
"Call the server_ping tool to verify the Metabase MCP server is running."
A successful response looks like:
{"ok": true, "server": "metabase-mcp", "version": "0.1.0"}Development
# Run tests
npm test
# Watch mode
npm run test:watch
# Lint
npm run lint
# Type check without building
npm run typecheck
# Build
npm run build
# Run server directly (requires env vars set)
npm startArchitecture
src/client.ts—MetabaseClientclass (HTTP,X-Api-Keyauth, typed errors) andMetabaseApiErrorsrc/index.ts— MCP server factory (createServer()), tool registrations, and stdio bootstrapsrc/types.ts— Hand-written TypeScript interfaces for Metabase API responses
All MCP server logging goes to stderr exclusively. stdout is reserved for the JSON-RPC protocol stream — any non-protocol bytes there would corrupt the MCP session.
Metabase Version
This server targets Metabase v0.59.x. APIs introduced after this version are not used.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/livingroot/metabase-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server