Delete a Compute Engine instance
AI agents call compute_delete_instance to permanently remove resources in Google Cloud — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a Compute Engine instance is an irreversible action that destroys infrastructure and potentially associated data. This cannot be undone without manual restoration from backups.
From the tool's definition Tool name 'compute_delete_instance' and description 'Delete a Compute Engine instance' explicitly indicate irreversible deletion of a cloud compute resource.
Attacks that exploit this kind of access
Delete a Compute Engine instance. It is categorised as a Destructive tool in the Google Cloud MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Google Cloud MCP server in PolicyLayer and add a rule for compute_delete_instance: 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 Google Cloud. Nothing to install.
compute_delete_instance 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 compute_delete_instance 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 compute_delete_instance. 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.
compute_delete_instance is provided by the Google Cloud MCP server (lockon-n/google-cloud-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 →