Cancel a fulfillment (unmark as shipped).
AI agents call cancel_fulfillment to permanently remove resources in AdminAgent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a fulfillment is a significant irreversible-in-practice action: it reverses a shipped status, potentially triggers carrier cancellations, invalidates tracking information, and disrupts downstream logistics.
From the tool's definition 'Cancel a fulfillment (unmark as shipped)' — reverses a fulfillment action, which can disrupt order processing, shipping workflows, and customer notifications in ways that may be difficult or impossible to undo operationally
Attacks that exploit this kind of access
Cancel a fulfillment (unmark as shipped). It is categorised as a Destructive tool in the AdminAgent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AdminAgent MCP server in PolicyLayer and add a rule for cancel_fulfillment: 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 AdminAgent. Nothing to install.
cancel_fulfillment 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_fulfillment 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_fulfillment. 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_fulfillment is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →