AI agents call query_tickets to retrieve information from Tickiti without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing tickets from a helpdesk system filtered by a saved view (perspective). It is a read-only query operation that has no side effects on the data. The blast radius of misuse is minimal—an attacker could view tickets they shouldn't see, but cannot modify, delete, or execute operations. This is classified as Read with low severity.
From the tool's definition Tool name 'query_tickets' and description 'List tickets for a perspective' indicates retrieval of ticket data with no modification or deletion capabilities mentioned.
Attacks that exploit this kind of access
List tickets for a perspective (saved view). Specify perspective_id or. It is categorised as a Read tool in the Tickiti MCP Server, which means it retrieves data without modifying state.
Register the Tickiti MCP server in PolicyLayer and add a rule for query_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 Tickiti. Nothing to install.
query_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 query_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 query_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.
query_tickets is provided by the Tickiti MCP server (tickiti/tickiti-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 →