AI agents call list_responses 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 only queries and retrieves existing response metadata and content from tickets. It has no side effects, does not modify data, execute code, delete anything, or involve financial transactions. The blast radius of misuse is minimal—at worst an AI could retrieve sensitive ticket information it shouldn't access, but the tool itself performs no destructive or risky operations.
From the tool's definition Tool name 'list_responses' and description indicate it retrieves responses on a ticket, displaying bodies, public/internal flags, author information. The verb 'list' and read-only retrieval of existing ticket response data with no modification capability.
Attacks that exploit this kind of access
List the responses on a ticket (bodies, public/internal flag, author and. 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 list_responses: 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.
list_responses 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 list_responses 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 list_responses. 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.
list_responses 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 →