// SCAN REPORT

Kubernetes MCP Server

49 tools. 14 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 4 Jul 2026

14 can modify or destroy data

35 read-only

49 tools total

Community server · catalogue entry verified 04/07/2026

How to control Kubernetes MCP Server ↓

TOOL MAP

What Kubernetes MCP Server exposes to your agents

Read (35) Write / Execute (9) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Kubernetes MCP Server tools

Destructive · High k8s_delete_configmap ConfigMaps store application configuration data in Kubernetes. Destructive · Critical k8s_delete_namespace Deleting a namespace is an irreversible destructive action that cascades to remove all pods, services, deployments, configmaps, secrets, and other resources within it. Destructive · High k8s_delete_pod Deleting a pod is a destructive action that cannot be undone. Destructive · Critical k8s_delete_resource The tool performs irreversible deletion of Kubernetes resources.

14 of Kubernetes MCP Server's 49 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Kubernetes MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Kubernetes MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "k8s_delete_configmap": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "k8s_apply_manifest": {
    "limits": [
      {
        "counter": "k8s_apply_manifest_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "k8s_current_context": {
    "limits": [
      {
        "counter": "k8s_current_context_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Kubernetes MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON KUBERNETES →

Instant setup, no code required.

FULL CATALOGUE

All 49 Kubernetes MCP Server tools

DESTRUCTIVE 5 tools

Destructive k8s_delete_configmap Delete a ConfigMap Destructive k8s_delete_namespace Delete a namespace (WARNING: This will delete all resources in the namespace) Destructive k8s_delete_pod Delete a pod Destructive k8s_delete_resource Delete a resource by type and name Destructive k8s_delete_secret Delete a secret

EXECUTE 4 tools

Execute k8s_exec_pod Execute a command in a pod container Execute k8s_restart_deployment Perform a rolling restart of a deployment Execute k8s_scale_deployment Scale a deployment to a specific number of replicas Execute k8s_scale_statefulset Scale a StatefulSet to a specific number of replicas

WRITE 5 tools

Write k8s_apply_manifest Apply a YAML or JSON manifest to the cluster Write k8s_create_configmap Create a ConfigMap from literal values Write k8s_create_namespace Create a new namespace Write k8s_create_secret Create a generic secret from literal values Write k8s_update_deployment_image Update the container image of a deployment

READ 35 tools

Read k8s_current_context Get the current kubectl context Read k8s_describe_deployment Get full description of a deployment including events and conditions Read k8s_describe_node Get full description of a node including conditions, capacity, and allocatable resources Read k8s_describe_pod Get full description of a pod including events Read k8s_describe_service Get full description of a service including endpoints Read k8s_get_all Get all common resources in a namespace Read k8s_get_cluster_info Get Kubernetes cluster information including server version and endpoints Read k8s_get_configmap Get ConfigMap details and data Read k8s_get_contexts List all available kubectl contexts Read k8s_get_daemonset Get DaemonSet details Read k8s_get_deployment Get detailed information about a deployment Read k8s_get_events Get cluster events, optionally filtered by namespace Read k8s_get_ingress Get Ingress details Read k8s_get_node Get detailed information about a specific node Read k8s_get_pod Get detailed information about a specific pod Read k8s_get_pod_logs Get logs from a pod container Read k8s_get_resource_yaml Get any resource as YAML Read k8s_get_secret Get secret metadata (values are base64 encoded) Read k8s_get_service Get detailed information about a service Read k8s_get_statefulset Get StatefulSet details Read k8s_list_configmaps List ConfigMaps in a namespace Read k8s_list_daemonsets List DaemonSets in a namespace Read k8s_list_deployments List deployments in a namespace or all namespaces Read k8s_list_ingresses List Ingresses in a namespace Read k8s_list_namespaces List all namespaces in the cluster Read k8s_list_nodes List all nodes in the cluster with their status, roles, and resource information Read k8s_list_pods List pods in a namespace or all namespaces Read k8s_list_secrets List secrets in a namespace (values are not shown) Read k8s_list_services List services in a namespace or all namespaces Read k8s_list_statefulsets List StatefulSets in a namespace Read k8s_rollout_history Get the rollout history of a deployment Read k8s_rollout_status Get the status of a deployment rollout Read k8s_rollout_undo Undo the last rollout of a deployment Read k8s_top_nodes Show resource usage (CPU/memory) for nodes Read k8s_top_pods Show resource usage (CPU/memory) for pods

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Kubernetes MCP Server

Can an AI agent delete data through the Kubernetes MCP Server MCP server? +

Yes. The Kubernetes MCP Server server exposes 5 destructive tools including k8s_delete_configmap, k8s_delete_namespace, k8s_delete_pod. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Kubernetes MCP Server? +

The Kubernetes MCP Server server has 5 write tools including k8s_apply_manifest, k8s_create_configmap, k8s_create_namespace. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Kubernetes MCP Server.

How many tools does the Kubernetes MCP Server MCP server expose? +

49 tools across 4 categories: Destructive, Execute, Read, Write. 35 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Kubernetes MCP Server? +

Register the Kubernetes MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Kubernetes MCP Server tool call.

Deterministic rules across all 49 Kubernetes MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON KUBERNETES →

Instant setup, no code required.

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