destroy_deployment
AI agents call destroy_deployment to permanently remove resources in Megaraptor MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call destroy_deployment doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Megaraptor MCP is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
destroy_deployment. It is categorised as a Destructive tool in the Megaraptor MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Megaraptor MCP server in PolicyLayer and add a rule for destroy_deployment: 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 Megaraptor MCP. Nothing to install.
destroy_deployment 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 destroy_deployment 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 destroy_deployment. 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.
destroy_deployment is provided by the Megaraptor MCP server (wagonbomb/megaraptor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.