Zendesk · Support
ZENDESK_LIST_TICKETS
List support tickets from the connected Zendesk account. Returns { tickets: [{ id, subject, status, priority, requester_id, assignee_id }], next_page, count }.
- Provider
- Zendesk
- Access
- Read
- Category
- Support
- Version
- v1
Input schema
{
"type": "object",
"properties": {
"perPage": {
"type": "number",
"description": "Tickets per page (default 25, max 100)."
},
"page": {
"type": "number",
"description": "Page number (default 1)."
}
},
"additionalProperties": false
}How to call it
Expose this tool to any MCP-capable agent (Claude, GPT, or your own) through CybrLink's MCP server. The agent calls zendesk_list_tickets with arguments matching the schema above.
CybrLink validates the input, injects the connected Zendesk credentials server-side, and runs a single scoped provider API call through the shared proxy — the same guarded path as the generic call_api tool. The raw secret never reaches the model, and the response is trimmed to just the fields the agent needs.
Frequently asked
- How do I let an AI agent zendesk list tickets?
- Connect Zendesk to CybrLink, then expose the `zendesk_list_tickets` tool to any MCP-capable agent (Claude, GPT, or a custom framework). The agent calls it with typed arguments; CybrLink injects the Zendesk credential server-side and runs one scoped API call. List support tickets from the connected Zendesk account. Returns { tickets: [{ id, subject, status, priority, requester_id, assignee_id }], next_page, count }.
- Does the AI model see my Zendesk credentials when using ZENDESK_LIST_TICKETS?
- No. CybrLink stores the credential in a token vault and injects it on the server for each call, so the model can read this data from Zendesk without the OAuth token or API key ever entering its context.