The Zendesk connector.
Support tickets, comments and help articles. Connect once with your own key. Every agent your team runs reads the same 6 tools under one permission model.
How access is governed
6
Read tools
Open by default. They run when called, and every call is logged with the endpoint, tool and capability.
0
Write tools
Zendesk exposes no write tools. Nothing it does mutates external state.
0
Destructive tools
Zendesk defines no destructive tools. Nothing here deletes data.
Defaults come from the capability on each tool definition, and an admin can tighten or open any tool individually. The endpoint's capability ceiling can only tighten that policy. An endpoint scoped to read never surfaces a write tool.
Every Zendesk tool
6 tools, named as the agent sees them.
- search_ticketsread
Find tickets with Zendesk search syntax (e.g. 'status:open priority:urgent tags:billing', 'requester:me@acme.com created>2026-01-01'). Use this first: it returns ticket ids that get_ticket and list_ticket_comments take. `type:ticket` is added for you when the query does not already name a type.
- get_ticketread
Get one ticket with its original description text. Takes a ticket id from search_tickets. Read the replies with list_ticket_comments.
- list_ticket_commentsread
List a ticket's comments (the conversation) as plain text, oldest first. `public: false` marks an internal agent note. Author ids resolve through list_users.
- list_usersread
List Zendesk users — use it to turn the requester_id / assignee_id / author_id numbers returned by the ticket tools into names and emails.
- list_organizationsread
List organizations (customer accounts). Use it to resolve the organization_id on a ticket, or to see which domains map to which account.
- search_help_center_articlesread
Full-text search the Help Center knowledge base. Use it to answer a customer question from published documentation instead of guessing.
Use it from any agent
The same Zendesk tools reach Claude Code, Cursor, Claude Desktop or your own agent through one MCP endpoint. The endpoint is scoped to a group, the token is issued per group and revocable from the dashboard, and an allowed-tool list and capability ceiling limit what it exposes. Reads run. Gated writes refuse unless an admin opens them. Destructive tools remain unavailable over MCP.
{
"mcpServers": {
"growth": {
"type": "http",
"url": "https://app.notara.ai/mcp/g/acme/growth",
"headers": {
"Authorization": "Bearer ntr_mcp_xxxxxxxxxxxxxxxxxxxx"
}
}
}
}The URL and token are placeholders. Real endpoints are issued per group from the dashboard.
Setup
- 01
Create a Zendesk API Token in your Zendesk account (where to find it). The key is yours: Notara stores it encrypted and never sees a bill.
- 02
Paste it into the Notara dashboard. Credentials can be scoped to the workspace or to one person.
- 03
The tools appear with their capability defaults already set. Tighten or open any of them per tool, then invite the agent to a channel or issue an MCP token.
Connect Zendesk once. Use it everywhere.
Use Notara directly, or bring us the workflow that needs to be redesigned and built.