AI agents use respond_to_ticket to create or update resources in Tickiti — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tickiti environment.
This tool creates or appends data to an existing ticket reversibly. Responses can be edited or deleted later, making it a Write operation rather than Destructive. The impact is medium severity because an agent could spam tickets, add misleading responses, or expose sensitive information via internal notes if misused, but the changes are not irreversible and do not result in data loss or financial harm.
From the tool's definition Tool description states 'Add a response to an existing ticket', which creates new data (a response/comment) attached to a ticket record. The ability to set is_internal=true indicates it modifies ticket state and metadata.
Attacks that exploit this kind of access
Add a response to an existing ticket. Set is_internal=true for a staff-only note. It is categorised as a Write tool in the Tickiti MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tickiti MCP server in PolicyLayer and add a rule for respond_to_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 Tickiti. Nothing to install.
respond_to_ticket is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the respond_to_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 respond_to_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.
respond_to_ticket 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 →