Data & Storage · Integration
Metabase
Add Metabase to your product for your customers, and give your AI agents governed access to it.
Embed a Metabase integration so your product can answer with the questions a customer's team already trusts, rather than a metric you defined separately. Each customer connects their own instance, cloud or self-hosted, so queries run under their credentials and their own data permissions apply. Questions and collections change as a business does, so which question your product runs is configuration per customer rather than code, and pagination and throttling are handled so a large result does not exhaust their allowance. The same governed connection powers in-product reporting and gives your AI agents scoped, audited read access.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers connect their own Metabase instance, cloud or self-hosted, so your product uses the questions their team already trusts.
Run a saved question or a query from inside your product and show the result where the work happens.
Read dashboards and collections per tenant so your product links to the report behind a number instead of rebuilding it.
Keep every query scoped to the tenant that authorised it, so their own data permissions apply.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent answers by running the customer's own saved Metabase question rather than approximating the number.
An agent cites the question behind a figure so a user can check the working, with each read audited.
An agent watches a metric and explains a change as soon as it appears.
Example prompt
Run this account's signup question in Metabase and tell me which channel moved.
Set up Metabase in 4 steps
- 01Enable the Metabase connector in your fastn dashboard.
- 02Have each customer authorise their own Metabase instance so queries run under their credentials.
- 03Map the questions, collections and fields your product uses, per customer.
- 04Call it from your product and expose the same connection to your agents through the MCP gateway.
Why teams use the Metabase integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Metabase integration without building it. Your customers connect their own Metabase account inside your product and work their records, datasets and fields there, with no per-customer code on your side.
- Handle the part that actually costs time: schemas differ per customer and change without notice, and volumes can be large. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a Metabase update is not your on-call problem.
- One integration serves your product and your agents. The same governed Metabase connection powers in-product features and gives AI agents scoped, audited access, so you read and write your customers' data where it already lives without wiring it twice.
Used by these teams
Compare with
Looker
Power BI
DomoOften used alongside
Tools the same teams tend to run next to Metabase, across other categories.
Anthropic Claude
OpenAI
Hugging FaceMetabase integration FAQ
How do I add a Metabase integration to my product?
Enable the Metabase connector in your fastn dashboard, then let each customer authenticate their own Metabase account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Metabase client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Metabase account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Metabase account and only ever sees their own records, datasets and fields. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this Metabase integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent answers by running the customer's own saved Metabase question rather than approximating the number.
Who maintains the Metabase integration?
fastn does. When Metabase changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Does the Metabase integration adapt when a customer's schema changes?
Schema and field mapping is configuration per customer, so a change on their side is a mapping update rather than a code change and a release on yours.
How are large Metabase reads handled?
Pagination and throttling are handled for you, and initial backfills are rate-limited so a large import does not exhaust a customer's API allowance.
What can I build with the Metabase integration?
A common starting point: connect their own Metabase instance, cloud or self-hosted, so your product uses the questions their team already trusts. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the Metabase integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Metabase does not change your per-connector cost. You can start free with 3 connected accounts.
Add Metabase to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.