AI agents call search_tickets to retrieve information from Zendesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries ticket data without modifying, deleting, or executing any operations. It has read-only semantics with minimal blast radius—an AI agent cannot cause harm by searching tickets, only by discovering information that was already accessible.
From the tool's definition Tool description states: 'Search and list Zendesk tickets.' The verbs 'search' and 'list' indicate retrieval operations. The description emphasizes returning data ('Returns full details') with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search and list Zendesk tickets. Returns full details with assignee/requester names, status, priority, tags. Max 100 per page. Query MUST include. It is categorised as a Read tool in the Zendesk MCP Server, which means it retrieves data without modifying state.
Register the Zendesk MCP server in PolicyLayer and add a rule for search_tickets: 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.
search_tickets is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_tickets 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 search_tickets. 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.
search_tickets 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 →