Cancel a fulfillment order (if still cancellable).
AI agents call fulfillment_cancel to permanently remove resources in Kiln — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Canceling a fulfillment order is an irreversible operation that destroys or terminates an order's active state. While not a data deletion in the database sense, it permanently changes the order lifecycle in a way that cannot be automatically reversed. This fits the Destructive category (actions that cannot be undone) more appropriately than Write (reversible modifications).
From the tool's definition Tool name "fulfillment_cancel" and description "Cancel a fulfillment order (if still cancellable)" indicate irreversible cancellation of an order state.
Attacks that exploit this kind of access
Cancel a fulfillment order (if still cancellable). It is categorised as a Destructive tool in the Kiln MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kiln MCP server in PolicyLayer and add a rule for fulfillment_cancel: 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 Kiln. Nothing to install.
fulfillment_cancel 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 fulfillment_cancel 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 fulfillment_cancel. 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.
fulfillment_cancel is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →