# Square AI connector guide

Connect Square data to AI agents with Combined. Explore customers, locations, shifts, 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 Square.
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

- Authentication: optional; Oauth authentication or API key
- Client ID: depends on the selected authentication/setup option
- Client Secret: depends on the selected authentication/setup option
- Refresh Token: depends on the selected authentication/setup option
- API key token: depends on the selected authentication/setup option
- Include Deleted Objects: optional
- Sandbox: required in the upstream source schema
- Start Date: optional

## Dataset reference

- customers; key: id
- locations; key: id
- shifts; key: id
- team_members; key: id
- team_member_wages; key: id
- items; update field: updated_at
- categories; update field: updated_at
- discounts; update field: updated_at
- taxes; update field: updated_at
- modifier_list; update field: updated_at
- refunds; key: id; update field: created_at
- inventory; key: catalog_object_id
- payments; key: id; update field: created_at
- orders; key: id; update field: updated_at
- bank_accounts; key: id
- cash_drawers; key: id
- loyalty; key: id

This is the upstream connector reference, version 1.7.26. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my Square data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to customers, locations, shifts, team_members, team_member_wages, items.
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/square
- Full guide: https://www.trycombined.com/connectors/square