# Zendesk Support AI connector guide

Connect Zendesk Support data to AI agents with Combined. Explore brands, deleted tickets, groups, 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 Zendesk Support.
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; OAuth2.0 with Refresh Token or API Token or OAuth2.0 (Legacy)
- Access Token: depends on the selected authentication/setup option
- 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
- Token Expiry Date: depends on the selected authentication/setup option
- API Token: depends on the selected authentication/setup option
- Email: depends on the selected authentication/setup option
- Access Token: depends on the selected authentication/setup option
- Client ID: depends on the selected authentication/setup option
- Client Secret: depends on the selected authentication/setup option
- [Deprecated] Should the connector read the second and further pages of data.: optional
- Number of concurrent threads: optional
- Page Size (ticket_comments): optional
- Start Date: optional
- Subdomain: required in the upstream source schema
- Tickets Search Lookback Window (days): optional

## Dataset reference

- brands
- deleted_tickets
- groups
- organizations
- satisfaction_ratings
- tags
- ticket_audits
- ticket_comments
- ticket_fields
- ticket_forms
- ticket_events
- ticket_metric_events
- ticket_metrics; key: id; update field: _ab_updated_at
- tickets
- users
- account_attributes
- attribute_definitions
- custom_roles
- schedules
- sla_policies
- topics
- user_fields
- automations
- categories
- sections
- articles; key: id
- article_attachments; key: id
- article_comments; key: id
- article_votes; key: id
- article_comment_votes; key: id
- audit_logs
- group_memberships
- macros
- organization_fields
- organization_memberships
- posts; key: id
- post_comment_votes; key: id
- post_comments; key: id
- post_votes; key: id
- ticket_activities
- side_conversations
- ticket_skips
- tickets_search; key: id; update field: updated_at
- triggers
- user_identities

This is the upstream connector reference, version 5.5.0. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my Zendesk Support data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to brands, deleted_tickets, groups, organizations, satisfaction_ratings, tags.
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/zendesk-support
- Full guide: https://www.trycombined.com/connectors/zendesk-support