delete_pod
AI agents call delete_pod to permanently remove resources in Kube — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes Kubernetes pods, which is an irreversible destructive action. It removes running container instances and cannot be undone without recreation. Although the description is empty, the name combined with the Kubernetes context and sibling tools (create_pod, describe_pod, get_logs, list_*) makes the destructive intent clear. Pod deletion is a high-impact operation that disrupts workloads.
From the tool's definition Tool name 'delete_pod' with no description. Matches destructive verb 'delete' operating on Kubernetes resources (pods). Deletion of pods is irreversible and terminates running containers.
Attacks that exploit this kind of access
delete_pod. It is categorised as a Destructive tool in the Kube MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kube MCP server in PolicyLayer and add a rule for delete_pod: 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 Kube. Nothing to install.
delete_pod 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_pod 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_pod. 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_pod is provided by the Kube MCP server (lochgeo/kube-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 →