AI agents call get_ticket 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 ticket information without modifying, deleting, or executing operations. While Zendesk tickets may contain sensitive customer data, the read-only nature makes this a low-severity information disclosure risk rather than a higher-impact category. Misuse would involve unauthorized access to ticket contents, not data destruction or financial transactions.
From the tool's definition Tool name 'get_ticket' and description 'Get full details of a single ticket by ID' indicate data retrieval only. The verb 'Get' and the absence of any modification language ('create', 'update', 'delete') confirm read-only semantics.
Attacks that exploit this kind of access
Get full details of a single ticket by ID including all comments, custom fields, and resolved names. 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 get_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.
get_ticket 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 get_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 get_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.
get_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 →