Cancel a request.
AI agents call cancel_incident to permanently remove resources in InvGate Service Desk — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling an incident/request is a destructive action in the sense that it terminates the workflow in an irreversible way. Unlike 'delete', cancellation may leave a record, but the operational state change (closing/voiding the request) cannot typically be undone, making it closer to Destructive than Write. The blast radius is high because an AI agent could inadvertently cancel active incidents affecting users.
From the tool's definition Cancel a request — cancellation is typically an irreversible state change that closes/terminates an incident permanently.
Attacks that exploit this kind of access
Cancel a request. It is categorised as a Destructive tool in the InvGate Service Desk MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the InvGate Service Desk MCP server in PolicyLayer and add a rule for cancel_incident: 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 InvGate Service Desk. Nothing to install.
cancel_incident is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cancel_incident 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 cancel_incident. 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.
cancel_incident is provided by the InvGate Service Desk MCP server (oci:ghcr.io/tracegazer/invgate-service-desk-mcp:0.2.0). 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 →