Discover · metabase.com

Rebuilding the Metabase MCP server: lessons for MCP tool design

Metabase metabase.com

An MCP server gives AI agents a set of tools for working in another app. Ours lets an agent do what you’d do in Metabase: find questions and dashboards, run queries and chart the results, build dashboards and documents, and set up alerts, all with your permissions. Our API could already do all of that. The hard part was turning it into tools a model actually uses well.

It took us two tries. The first version, in Metabase 60, wrapped our REST API, and models had a hard time with it. So we rebuilt it for Metabase 64 refined it in the next release, and we’ll keep doing so. This post covers what went wrong the first time, what we changed and why, and what we’d tell anyone building an MCP server or an agent of their own. Most of it isn’t specific to Metabase.

More ways to use this
Open on another device
Scan this QR code to open the same public page

Scan to open this page. Your saved notes and account access are not included.

Download QR code

Open the page link

Names and references

  1. Design — person
  2. Server — person

In the piece

Named in it

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

Also from Metabase

  1. From Toronto Hackathon to Stockholm meetup: Metabase data app world tourmetabase.com
  2. 'Wait, you don't have a semantic layer yet?' AI analytics readiness pulsemetabase.com
  3. As humans write less code: workloads shift from human to agent verification with iterative test suitesmetabase.com
  4. We don't use PHPmetabase.com
  5. Making pivot tables faster with GROUPING SETSmetabase.com
  6. The bottleneck moved: how to build a semantic layer for AI Analyticsmetabase.com