Delete a pod
AI agents call k8s_delete_pod to permanently remove resources in Kubernetes MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a pod is a destructive action that cannot be undone. The pod and its state are permanently removed from the cluster, potentially causing service interruption, data loss if the pod held ephemeral state, and disruption to dependent applications. This falls squarely into the Destructive category as the primary risk.
From the tool's definition Tool name explicitly states 'delete_pod' and description confirms 'Delete a pod'. Deletion of Kubernetes pods is an irreversible operation that terminates running containers and their workloads.
Attacks that exploit this kind of access
Delete a pod. It is categorised as a Destructive tool in the Kubernetes MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kubernetes MCP Server MCP server in PolicyLayer and add a rule for k8s_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 Kubernetes MCP Server. Nothing to install.
k8s_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 k8s_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 k8s_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.
k8s_delete_pod is provided by the Kubernetes MCP Server MCP server (mjrestivo16/mcp-kubernetes). 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 →