delete_customer
AI agents call delete_customer 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.
Deletion of customer records cannot be undone and represents permanent loss of data. While not as severe as some financial impacts (hence 'high' not 'critical'), this is clearly Destructive rather than Write. The empty description lowers confidence slightly, but the name itself is unambiguous.
From the tool's definition Tool name is 'delete_customer' with no description provided. The verb 'delete' combined with the object 'customer' indicates irreversible removal of customer data from a Shopify store.
Attacks that exploit this kind of access
delete_customer. 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 delete_customer: 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.
delete_customer 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_customer 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_customer. 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_customer 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 →