Metabase MCP Server

Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the Streamable HTTP transport and builds on Metabase's Agent API to expose tools for searching, exploring, querying, and visualizing data — all scoped to the connecting user's permissions.

Endpoint

The MCP server is available at:

https://{your-metabase.example.com}/api/mcp

Connecting a client

Point any MCP-compatible client at the /api/mcp endpoint. For example, with Claude Code:

claude mcp add metabase https://{your-metabase.example.com}/api/mcp --transport streamable-http

For Claude Desktop, create a custom connector using the same URL.

For Cursor, open Settings > MCP and add a new server with the type set to streamable-http and the URL:

https://{your-metabase.example.com}/api/mcp

Authentication

MCP clients authenticate via OAuth 2.0. Metabase runs its own embedded OAuth server — no external provider is needed.

The flow for a first-time connection:

1. The client discovers Metabase's OAuth endpoints.

2. The client registers itself with Metabase.

3. The user is redirected to Metabase to log in and approve the connection.

4. The client receives an access token scoped to the user's Metabase permissions.

Browser-based sessions (cookie auth) are also supported and receive unrestricted scopes.

Scopes

Access tokens are scoped to limit what tools a client can use:

Wildcard patterns (e.g. agent:*) match any scope with that prefix.

OAuth protected resource metadata is available at:

/.well-known/oauth-protected-resource/api/mcp

By default our consent screen grants access to all scopes without the opportunity to customize.

Available tools

The MCP server exposes these tools, dynamically generated from the Agent API endpoint metadata:

Query results are limited to 200 rows per request. When more rows are available, the response includes a continuation_token that can be passed back to fetch the next page.

Resources

The server exposes MCP resources so clients can fetch supplementary content by URI without inflating tool descriptions.

Supported JSON-RPC methods

Requests can be sent individually or as a JSON-RPC batch. The server responds with JSON or SSE depending on the Accept header.

Architecture

The implementation lives in these files:

• api.clj — The HTTP handler. Parses JSON-RPC requests, validates authentication and session headers, enforces origin checks (DNS rebinding protection), and dispatches to the appropriate method. Supports both JSON and SSE response formats.

• tools.clj — Tool dispatch and manifest generation. Builds the tool list from Agent API endpoint metadata, checks scopes, and routes tool calls through synthetic Agent API requests.

• resources.clj — MCP resource registry and handlers. Holds documentation resources (like the construct_query reference) keyed by URI, with scope-based access control on resources/list and resources/read.

• scope.clj — Scope matching logic. Supports exact matches, wildcard patterns, and the ::unrestricted sentinel for session-based auth.

Request flow

MCP client
  → POST /api/mcp (JSON-RPC)
  → Origin + session validation
  → Auth: OAuth bearer token or browser session
  → Scope check against requested tool
  → Synthetic request to Agent API endpoint
  → Response materialized as MCP content
  → JSON or SSE back to client

Further reading

• MCP user docs

• Agent API source

• Model Context Protocol specification