# RevenueCat AI connector guide

Connect RevenueCat data to AI agents with Combined. Explore projects, apps, metrics overview, source setup, MCP access and read-only business queries.

Combined offers 1,125 connectors across catalog sources and connectors generated through desktop automation.

## Connect

1. Open Combined Connected Apps and select RevenueCat.
2. Authorize the source and choose the relevant datasets.
3. Complete a first sync, then grant your agent access through the Set up or Access workspace.
4. Discover the actual source schemas before querying.

## Setup reference

- API Key: required in the upstream source schema
- Start date: required in the upstream source schema

## Dataset reference

- projects; key: id; update field: created_at
- apps; key: id; update field: created_at
- metrics_overview; key: id
- customers; key: id; update field: last_seen_at
- customers_subscriptions; key: id; update field: starts_at
- customers_purchases; key: id; update field: purchased_at
- customers_active_entitlements; key: entitlement_id; update field: expires_at
- customers_aliases; key: id; update field: created_at
- customers_invoices; key: id; update field: issued_at
- entitlements; key: id; update field: created_at
- entitlements_products; key: id, entitlement_id; update field: created_at
- offerings; key: id; update field: created_at
- offerings_packages; key: id; update field: created_at
- offerings_packages_products; key: id, package_id; update field: created_at
- products; key: id; update field: created_at

This is the upstream connector reference, version 0.1.45. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my RevenueCat data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to projects, apps, metrics_overview, customers, customers_subscriptions, customers_purchases.
Check the last successful sync and report the available date coverage.
Propose three useful questions based on the fields actually available.
For the question I choose, run read-only SQL over the complete matching dataset.
Use a bounded result; include source names, time window and query receipt.
Ask for a missing join key or metric definition instead of inventing one.

## Links

- Combined: https://www.trycombined.com/
- Setup: https://www.trycombined.com/docs/getting-started/onboarding
- MCP: https://www.trycombined.com/docs/integrations/mcp
- Pricing: https://www.trycombined.com/pricing
- Upstream source reference: https://docs.airbyte.com/integrations/sources/revenuecat
- Full guide: https://www.trycombined.com/connectors/revenuecat