# Plaid AI connector guide

Connect Plaid data to AI agents with Combined. Explore balance, transaction, 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 Plaid.
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

- Access Token: required in the upstream source schema
- API Key: required in the upstream source schema
- Client ID: required in the upstream source schema
- Plaid Environment: required in the upstream source schema
- Start Date: optional

## Dataset reference

- balance; key: account_id
- transaction; key: transaction_id; update field: date

This is the upstream connector reference, version 0.5.14. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my Plaid data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to balance, transaction.
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/plaid
- Full guide: https://www.trycombined.com/connectors/plaid