Delete purchase order by ID
AI agents call delete_order to permanently remove resources in Petstore MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a purchase order cannot be undone and results in permanent loss of data. This is a destructive action with potential business impact (loss of order history, audit trail disruption, financial record inconsistencies).
From the tool's definition Tool name is 'delete_order' and description states 'Delete purchase order by ID' — the verb 'Delete' and action of removing a purchase order record are irreversible operations.
Attacks that exploit this kind of access
Delete purchase order by ID. It is categorised as a Destructive tool in the Petstore MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Petstore MCP Server MCP server in PolicyLayer and add a rule for delete_order: 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 Petstore MCP Server. Nothing to install.
delete_order 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 delete_order 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 delete_order. 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.
delete_order is provided by the Petstore MCP Server MCP server (raghavendraprakash/mcpforrestapis). 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 →