Zendesk

27 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated:

7 can modify or destroy data
20 read-only
27 tools total

Community server · catalogue entry verified 03/07/2026

How to control Zendesk ↓

What Zendesk exposes to your agents

Read (20) Write / Execute (7) Destructive / Financial (0)
High Risk

The most dangerous Zendesk tools

7 of Zendesk's 27 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Zendesk

PolicyLayer is an MCP gateway — it sits between your AI agents and Zendesk, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "add_comment": {
    "limits": [
      {
        "counter": "add_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "count_tickets": {
    "limits": [
      {
        "counter": "count_tickets_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Zendesk — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ZENDESK →

Instant setup, no code required.

All 27 Zendesk tools

READ 20 tools
Read count_tickets Count ANY Zendesk tickets using flexible search queries. Returns EXACT total count. Query MUST include Read count_view Get ticket count for a specific Zendesk view. Read get_agent_performance_today Get agent performance ranking by tickets solved on a date. Returns names, counts, and sample tickets. Read get_organization Get details of a Zendesk organization by ID. Read get_ticket Get full details of a single ticket by ID including all comments, custom fields, and resolved names. Read get_ticket_audits Get audit history for a ticket (status changes, reassignments, comments). Read get_ticket_comments Get all comments and private notes for a ticket. Read get_trigger Get full details of a single Zendesk trigger by ID. Read get_user Get details of a Zendesk user by ID. Returns name, email, role, organization, tags. Read get_view Get details of a Zendesk view by ID (title, conditions, execution settings). Read list_automations List all Zendesk automations (time-based business rules). Automations fire based on time conditions (e.g. tick Read list_groups List all agent groups in the Zendesk instance. Groups organize agents into teams for routing and assignment. Read list_macros List all Zendesk macros (prepared responses and actions agents can apply to tickets with one click). Includes Read list_ticket_fields List all ticket fields including custom fields with their types and options. Read list_triggers List all Zendesk triggers (business rules) with conditions and actions. Read list_view_tickets List tickets in a specific Zendesk view with pagination. Read search_organizations Search for Zendesk organizations by name. Read search_tickets Search and list Zendesk tickets. Returns full details with assignee/requester names, status, priority, tags. M Read search_triggers Search Zendesk triggers by title. Read search_users Search for Zendesk users by name or email.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Zendesk

How do I prevent bulk modifications through Zendesk? +

The Zendesk server has 7 write tools including add_comment, add_ticket_tags, bulk_solve_tickets_by_type. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Zendesk.

How many tools does the Zendesk MCP server expose? +

27 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Zendesk? +

Register the Zendesk MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Zendesk tool call.

Deterministic rules across all 27 Zendesk tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

27 Zendesk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.