Skip to content
Custom Connectors

Connect Metabase to Claude Code

Let Claude create questions and build dashboards in Metabase. From the terminal, inside the sessions where you already work.

How do you connect Metabase to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Metabase, you add a Metabase MCP server: a small hosted service that exposes Metabase's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Metabase account. No API keys pasted into config files.

claude mcp add --transport http metabase https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Metabase once connected?

Full read-write Metabase access lets Claude create or update a saved question, build and arrange a dashboard, manage collections and permissions, and refresh queries against your warehouse. The dashboard assembly and metric definitions that used to mean manual clicking happen inside the instance where your data already lives.

  • Create a saved question from a natural-language prompt and a chosen data source
  • Build or update a dashboard and arrange its cards and filters
  • Organize questions and dashboards into collections
  • Edit an existing question's query, visualization, or display settings
  • Set up an alert or schedule a subscription after you approve it
  • Archive stale questions and dashboards as you clean up a collection

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Metabase access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Metabase API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Metabase changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Metabase connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Metabase connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Metabase account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Metabase's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Metabase?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Metabase account it signs in with. Revoking access is one click in Metabase.

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.