// SCAN REPORT

Multi Cluster Kubernetes MCP Server

57 tools. 26 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

26 can modify or destroy data

31 read-only

57 tools total

Community server · catalogue entry verified 11/06/2026

How to control Multi Cluster Kubernetes MCP Server ↓

TOOL MAP

What Multi Cluster Kubernetes MCP Server exposes to your agents

Read (31) Write / Execute (23) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Multi Cluster Kubernetes MCP Server tools

Destructive · Critical k8s_delete_ns Deleting a Kubernetes namespace is an irreversible operation that destroys all resources within it (pods, services, configmaps, volumes, etc.). Destructive · Critical k8s_delete_resource Deletion of Kubernetes resources (pods, deployments, services, configmaps, secrets, storage volumes, etc.) is irreversible and cannot be undone. Destructive · High k8s_drain_node Draining a node forcibly evicts all running pods from that node. Execute · High k8s_pod_exec This tool allows arbitrary command execution within Kubernetes pods/containers.

26 of Multi Cluster Kubernetes MCP Server's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Multi Cluster Kubernetes MCP Server

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. These are the rules we recommend:

Deny destructive operations

{
  "k8s_delete_ns": {
    "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_untaint_node": {
    "limits": [
      {
        "counter": "k8s_untaint_node_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "k8s_apis": {
    "limits": [
      {
        "counter": "k8s_apis_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 Multi Cluster 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 MULTI CLUSTER KUBERNETES →

Free to start. No card required.

FULL CATALOGUE

All 57 Multi Cluster Kubernetes MCP Server tools

DESTRUCTIVE 3 tools

Destructive k8s_delete_ns Delete a Kubernetes namespace and all resources within it. Destructive k8s_delete_resource Delete a Kubernetes resource. Supports all common resource types Destructive k8s_drain_node Drain a node by evicting all pods, preparing it for maintenance.

EXECUTE 7 tools

Execute k8s_pod_exec Execute a command inside a running container. Supports quoted arguments Execute k8s_rollout_restart Trigger a rolling restart of a deployment, daemonset, or statefulset. Execute k8s_run_pod Create and run a pod with the specified container image. Execute k8s_scale_resource Scale a deployment, statefulset, or replicaset to the specified number of replicas. Execute k8s_rollout_pause Pause an in-progress rollout for a deployment, daemonset, or statefulset. Execute k8s_rollout_undo Roll back a deployment, daemonset, or statefulset to a previous revision. Execute k8s_rollout_resume Resume a previously paused rollout for a deployment, daemonset, or statefulset.

WRITE 16 tools

Write k8s_untaint_node Remove a taint from a node. Omit effect to remove all taints with the given key. Write k8s_cordon_node Mark a node as unschedulable. Existing pods continue running Write k8s_expose_resource Expose a deployment or pod as a new Kubernetes Service. Write k8s_uncordon_node Mark a previously cordoned node as schedulable again. Write k8s_annotate_resource Add or update annotations on a Kubernetes resource. Write k8s_apply_resource Apply a configuration to a resource (create if it doesn't exist, update if it does). Write k8s_autoscale_resource Configure a Horizontal Pod Autoscaler (HPA) for a deployment, statefulset, or replicaset. Write k8s_create_configmap_resource Create a new Kubernetes ConfigMap with the specified key-value data pairs. Write k8s_create_ns Create a new Kubernetes namespace. Write k8s_create_resource Create a Kubernetes resource from YAML or JSON content. Write k8s_create_secret_resource Create a new Kubernetes Secret. Values in data will be automatically base64-encoded. Write k8s_label_resource Add or update labels on a Kubernetes resource. Write k8s_patch_resource Update specific fields of a resource using a strategic merge patch. Write k8s_set_resources_for_container Set resource limits and requests for containers in a deployment, statefulset, or daemonset. Write k8s_taint_node Add a taint to a node. Taints prevent pods without matching tolerations from being scheduled. Write k8s_update_resources Update CPU/memory requests and limits for a specific container in a deployment,

READ 31 tools

Read k8s_apis List all available API groups and resources in the Kubernetes cluster. Read k8s_cluster_info Get a comprehensive health summary of the entire Kubernetes cluster. Read k8s_crds List all Custom Resource Definitions (CRDs) installed in the cluster. Read k8s_describe Show detailed information about a resource, similar to 'kubectl describe'. Read k8s_diagnose_application k8s_diagnose_application Read k8s_get_clusterrolebindings List RBAC ClusterRoleBindings showing cluster-wide role assignments. Read k8s_get_clusterroles List RBAC ClusterRoles with their permission rules. Read k8s_get_configmap_detail Get a Kubernetes ConfigMap with its full data contents. Read k8s_get_contexts List all available Kubernetes contexts from all kubeconfig files. Read k8s_get_cronjobs List Kubernetes CronJobs with schedule, suspension status, active jobs, Read k8s_get_events List Kubernetes events in a namespace, sorted by most recent first. Read k8s_get_jobs List Kubernetes Jobs with completion status, active/succeeded/failed counts, Read k8s_get_namespaces List all namespaces in a Kubernetes cluster. Read k8s_get_network_policies List NetworkPolicies that control pod-to-pod and pod-to-external traffic. Read k8s_get_nodes List all nodes in a Kubernetes cluster with status, roles, capacity, and version info. Read k8s_get_pod_logs Get logs from a Kubernetes pod. For multi-container pods, logs from the first container Read k8s_get_pvcs List PersistentVolumeClaims (PVCs) with status, capacity, access modes, Read k8s_get_pvs List PersistentVolumes (PVs) in the cluster with capacity, access modes, Read k8s_get_resource Get the complete definition of a single Kubernetes resource. Read k8s_get_resources List Kubernetes resources of a specified kind (e.g., Pod, Deployment, Service, Ingress). Read k8s_get_rolebindings List RBAC RoleBindings showing which subjects (users, groups, service accounts) Read k8s_get_roles List RBAC Roles with their permission rules. Read k8s_get_secret_detail Get a Kubernetes Secret. By default shows only key names for security. Read k8s_get_service_accounts List Kubernetes ServiceAccounts. ServiceAccounts provide pod-level identity Read k8s_get_storage_classes List StorageClasses in the cluster with provisioner, reclaim policy, Read k8s_list_configmap List Kubernetes ConfigMaps with their key names. Read k8s_list_secret List Kubernetes Secrets with metadata (keys only, values hidden for security). Read k8s_rollout_history Get the revision history of a deployment, daemonset, or statefulset. Read k8s_rollout_status Get the rollout status of a deployment, daemonset, or statefulset. Read k8s_top_nodes Display CPU and memory usage of all nodes in the cluster. Read k8s_top_pods Display CPU and memory usage of pods, broken down by container.

EXPLORE

Related servers

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

FAQ

Questions about Multi Cluster Kubernetes MCP Server

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

Yes. The Multi Cluster Kubernetes MCP Server server exposes 3 destructive tools including k8s_delete_ns, k8s_delete_resource, k8s_drain_node. 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 Multi Cluster Kubernetes MCP Server? +

The Multi Cluster Kubernetes MCP Server server has 16 write tools including k8s_untaint_node, k8s_cordon_node, k8s_expose_resource. 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 Multi Cluster Kubernetes MCP Server.

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

57 tools across 4 categories: Destructive, Execute, Read, Write. 31 are read-only. 26 can modify, create, or delete data.

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

Register the Multi Cluster 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 Multi Cluster Kubernetes MCP Server tool call.

Deterministic rules across all 57 Multi Cluster Kubernetes MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MULTI CLUSTER KUBERNETES →

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.