AI agents use edit_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.
This tool modifies ticket data reversibly—fields like status, priority, subject, assignee, tags, and custom fields can be changed but are not permanently destroyed. This is a Write operation. Severity is high because misuse could redirect tickets to wrong assignees, change priorities inappropriately, or alter ticket status to hide issues, affecting support operations and customer experience.
From the tool's definition Tool description states 'Edit fields on a Zendesk ticket. Supports: status, priority, subject, assignee_id, tags, custom_fields.' The verb 'Edit' and modification of ticket fields (status, priority, assignee) indicate data modification operations.
Attacks that exploit this kind of access
Edit fields on a Zendesk ticket. Supports: status, priority, subject, assignee_id, tags, custom_fields. 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 edit_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.
edit_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 edit_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 edit_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.
edit_ticket is provided by the Zendesk MCP server (kalchevs/zendesk-mcp). 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 →