Remove a destination from a hook.
AI agents call delete_destination to permanently remove resources in Zhook — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes a destination configuration from the webhook/hook system. Once removed, the destination cannot be recovered without manual reconfiguration. While the blast radius is not system-wide, deletion of active destinations could cause webhook events to be lost or fail to deliver, resulting in operational disruption.
From the tool's definition Tool name is 'delete_destination' which explicitly indicates deletion. Description states 'Remove a destination from a hook,' using the verb 'Remove' which denotes permanent removal of a configured resource.
Attacks that exploit this kind of access
Remove a destination from a hook. It is categorised as a Destructive tool in the Zhook MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zhook MCP server in PolicyLayer and add a rule for delete_destination: 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 Zhook. Nothing to install.
delete_destination 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_destination 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_destination. 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_destination is provided by the Zhook MCP server (zhookteam/zhook-mcp). 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 →