AI agents use create_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 creates new tickets in Zendesk, which are persistent records that represent customer support interactions. While creation is reversible via deletion (making it Write rather than Destructive), the high severity reflects that an AI agent could maliciously or erroneously create large numbers of tickets, spam the support system, or create tickets with misleading/sensitive information.
From the tool's definition Tool name 'create_ticket' and description 'Create a new Zendesk ticket' indicate irreversible creation of a new data record in Zendesk. The sibling tool 'update_ticket' suggests modification capabilities in this server.
Attacks that exploit this kind of access
Create a new Zendesk ticket. 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 create_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.
create_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 create_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 create_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.
create_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 →