# Harvest AI connector guide

Connect Harvest data to AI agents with Combined. Explore time entries, projects, clients, 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 Harvest.
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

- Account ID: required in the upstream source schema
- Authentication mechanism: optional; Authenticate via Harvest (OAuth) or Authenticate with Personal Access Token
- 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
- Personal Access Token: depends on the selected authentication/setup option
- Number of Concurrent Threads: optional
- End Date: optional
- Start Date: required in the upstream source schema

## Dataset reference

- time_entries; key: id; update field: updated_at
- projects; key: id; update field: updated_at
- clients; key: id; update field: updated_at
- users; key: id; update field: updated_at
- roles; key: id; update field: updated_at
- tasks; key: id; update field: updated_at
- contacts; key: id; update field: updated_at
- task_assignments; key: id; update field: updated_at
- time_projects; update field: to
- user_assignments; key: id; update field: updated_at
- company
- invoices; key: id; update field: updated_at
- project_assignments; key: id; update field: updated_at
- time_tasks; update field: to
- estimate_item_categories; key: id; update field: updated_at
- estimates; key: id; update field: updated_at
- expense_categories; key: id; update field: updated_at
- expenses; key: id; update field: updated_at
- invoice_item_categories; key: id; update field: updated_at
- expenses_categories; update field: to
- expenses_clients; update field: to
- expenses_projects; update field: to
- expenses_team; update field: to
- project_budget
- time_clients; update field: to
- time_team; update field: to
- uninvoiced; update field: to
- estimate_messages; key: id; update field: updated_at
- invoice_messages; key: id; update field: updated_at
- invoice_payments; key: id; update field: updated_at
- billable_rates; key: id
- cost_rates; key: id

This is the upstream connector reference, version 1.2.48. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my Harvest data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to time_entries, projects, clients, users, roles, tasks.
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/harvest
- Full guide: https://www.trycombined.com/connectors/harvest