Critical Risk →

k8s_delete_ns

Delete a Kubernetes namespace and all resources within it.

How to control k8s_delete_ns ↓

What k8s_delete_ns does on Multi Cluster Kubernetes MCP Server

AI agents call k8s_delete_ns to permanently remove resources in Multi Cluster Kubernetes MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why k8s_delete_ns needs a policy

Deleting a Kubernetes namespace is an irreversible operation that destroys all resources within it (pods, services, configmaps, volumes, etc.). This cannot be undone and represents a complete loss of infrastructure and data at the namespace scope. This is categorized as Destructive (most severe) rather than Execute because the operation is inherently destructive and irreversible.

From the tool's definition Tool name 'k8s_delete_ns' combined with description 'Delete a Kubernetes namespace and all resources within it' explicitly performs deletion of a namespace and all contained resources.

Documented attack patterns abuse exactly the kind of access k8s_delete_ns gives an agent:

How to control k8s_delete_ns

PolicyLayer is an MCP gateway — it sits between your AI agents and Multi Cluster Kubernetes MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for k8s_delete_ns:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "k8s_delete_ns"
  ]
}

k8s_delete_ns disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Multi Cluster Kubernetes MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about k8s_delete_ns

What does the k8s_delete_ns tool do? +

Delete a Kubernetes namespace and all resources within it. It is categorised as a Destructive tool in the Multi Cluster Kubernetes MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on k8s_delete_ns? +

Register the Multi Cluster Kubernetes MCP Server MCP server in PolicyLayer and add a rule for k8s_delete_ns: 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 Multi Cluster Kubernetes MCP Server. Nothing to install.

What risk level is k8s_delete_ns? +

k8s_delete_ns is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit k8s_delete_ns? +

Yes. Add a rate_limit block to the k8s_delete_ns 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.

How do I block k8s_delete_ns completely? +

Set action: deny in the PolicyLayer policy for k8s_delete_ns. 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.

What MCP server provides k8s_delete_ns? +

k8s_delete_ns is provided by the Multi Cluster Kubernetes MCP Server MCP server (razvanmacovei/k8s-multicluster-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Multi Cluster Kubernetes MCP Server tool call.

Start from Multi Cluster Kubernetes MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

57 Multi Cluster Kubernetes MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.