AI agents call count_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 queries and counts existing ticket data without creating, modifying, deleting, or executing external operations. It is purely informational retrieval, making it a Read category tool. The blast radius of misuse is minimal—an agent could only obtain aggregate statistics about tickets. Severity is low because counting data poses no risk to ticket integrity, financial systems, or system operations.
From the tool's definition Tool description states "Count ANY Zendesk tickets using flexible search queries. Returns EXACT total count." The verb 'count' and phrase 'returns total count' indicate data retrieval with no modification or deletion of tickets.
Attacks that exploit this kind of access
Count ANY Zendesk tickets using flexible search queries. Returns EXACT total count. 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 count_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.
count_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 count_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 count_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.
count_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 →