AI agents use update_ticket to create or update resources in Zendesk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zendesk environment.
The tool creates or modifies data without permanent deletion. While ticket updates can affect workflows and SLAs, the changes are reversible (status can be re-set, assignee can be changed again). However, severity is high because misuse could disrupt customer support operations, reassign critical tickets inappropriately, or alter ticket priority in ways that violate SLAs.
From the tool's definition update_ticket updates fields on an existing Zendesk ticket (status, priority, assignee_id). This modifies ticket state in Zendesk, making it a Write operation that changes existing data reversibly.
Attacks that exploit this kind of access
Update fields on an existing Zendesk ticket (e.g., status, priority, assignee_id). It is categorised as a Write tool in the Zendesk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zendesk MCP server in PolicyLayer and add a rule for update_ticket: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Zendesk. Nothing to install.
update_ticket is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_ticket rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update_ticket. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update_ticket is provided by the Zendesk MCP server (reminia/zendesk-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →