Data & Storage · Integration
Looker
Add Looker to your product for your customers, and give your AI agents governed access to it.
Embed a Looker integration so your product can show numbers that come from the model a customer's analysts already maintain, instead of a metric you defined separately and have to defend. Each customer connects their own Looker instance, so queries run under their credentials and their own access rules apply. Because a Looker model changes as the business does, field and query mapping is configuration per customer rather than code on your side, and pagination and throttling are handled for you so a large result set does not exhaust a customer's 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 Looker instance so your product renders results from the models their analysts maintain.
Run a query against a customer's Explore from inside your product and show the answer where the decision is made.
Read a customer's Looks and dashboards so your product can link to the report behind a number instead of recreating it.
Keep every query scoped to the tenant that authorised it, so a customer's model and data stay theirs.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent answers a data question by querying the customer's own Looker model instead of approximating it.
An agent cites the Look behind a figure so a user can check the working, with each read audited.
An agent watches a metric in Looker and explains the move when it crosses a threshold.
Example prompt
Run this account's revenue Look in Looker and tell me which segment moved.
Set up Looker in 4 steps
- 01Enable the Looker connector in your fastn dashboard.
- 02Have each customer authorise their own Looker instance so queries run under their credentials.
- 03Map the Looks, Explores 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 Looker integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Looker integration without building it. Your customers connect their own Looker 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 Looker update is not your on-call problem.
- One integration serves your product and your agents. The same governed Looker 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
Power BI
BigQuery
MetabaseOften used alongside
Tools the same teams tend to run next to Looker, across other categories.
Anthropic Claude
OpenAI
Hugging FaceLooker integration FAQ
How do I add a Looker integration to my product?
Enable the Looker connector in your fastn dashboard, then let each customer authenticate their own Looker account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Looker client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Looker account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Looker 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 Looker 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 a data question by querying the customer's own Looker model instead of approximating it.
Who maintains the Looker integration?
fastn does. When Looker 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 Looker 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 Looker 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 Looker integration?
A common starting point: connect their own Looker instance so your product renders results from the models their analysts maintain. 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 Looker integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Looker does not change your per-connector cost. You can start free with 3 connected accounts.
Add Looker to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.