// SCAN REPORT

Kubernetes MCP Server

65 tools. 21 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

21 can modify or destroy data

44 read-only

65 tools total

Community server · catalogue entry verified 30/06/2026

How to control Kubernetes MCP Server ↓

TOOL MAP

What Kubernetes MCP Server exposes to your agents

Read (44) Write / Execute (17) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Kubernetes MCP Server tools

Destructive · Critical delete_deployment Deleting a deployment is a destructive operation that cannot be undone. Destructive · High delete_pod Deletion of pods in Kubernetes is an irreversible operation that terminates running containers and removes the resource state. Destructive · High delete_replicaset Deleting a ReplicaSet is a destructive operation that cannot be undone and will result in the loss of replica pod instances. Destructive · High delete_service Deleting a Kubernetes service is a destructive operation that cannot be undone without manual intervention.

21 of Kubernetes MCP Server's 65 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

{
  "delete_deployment": {
    "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

{
  "create_deployment": {
    "limits": [
      {
        "counter": "create_deployment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_configmaps": {
    "limits": [
      {
        "counter": "get_configmaps_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 65 Kubernetes MCP Server tools

DESTRUCTIVE 4 tools

Destructive delete_deployment Delete a deployment Destructive delete_pod Delete a pod Destructive delete_replicaset Delete a ReplicaSet Destructive delete_service Delete a service

EXECUTE 5 tools

Execute pause_deployment Pause a deployment Execute resume_deployment Resume a paused deployment Execute rollback_deployment Rollback a deployment to a specific revision Execute scale_deployment Scale a deployment to a specific number of replicas Execute scale_replicaset Scale a ReplicaSet to a specific number of replicas

WRITE 12 tools

Write create_deployment Create a new deployment Write create_deployment_with_health_checks Create a deployment with liveness and readiness probes Write create_deployment_with_resources Create a deployment with resource limits and requests Write create_deployment_with_strategy Create a deployment with specified update strategy Write create_pod Create a pod Write create_replicaset Create a new ReplicaSet Write create_service Create a new service Write create_service_account Create a new service account Write patch_service Patch a service with specific changes Write update_deployment Update an existing deployment Write update_replicaset Update an existing ReplicaSet Write update_service Update an existing service

READ 44 tools

Read get_configmaps Get all configmaps Read get_cronjobs Get all cronjobs Read get_current_stock_price Get Current Stock Price for a given Ticker Symbol Read get_deployment get_deployment Read get_deployment_details Get detailed information about a specific deployment Read get_deployment_events Get events related to a deployment Read get_deployment_history Get the revision history of a deployment Read get_deployment_rollout_status Get the rollout status of a deployment Read get_deployments Get all deployments Read get_endpoints Get all endpoints Read get_events Get all events from all namespaces Read get_historical_stock_splits Get list of historical stock splits Read get_ingress Get all ingress Read get_jobs Get all jobs Read get_namespaces Get all namespaces Read get_nodes Get all nodes Read get_pod_details Get detailed information about a specific pod Read get_pod_events Get events related to a pod Read get_pod_health_check Get health check configuration for a pod Read get_pod_logs Get logs from a pod Read get_pod_metrics Get resource usage metrics for a pod Read get_pod_network_policy Get network policy information for a pod Read get_pod_security_context Get security context information for a pod Read get_pod_volumes Get volume information for a pod Read get_pods Get all pods in a given namespace Read get_pods_for_all_namespaces Get pods for all namespaces Read get_pv Get all pv Read get_pvc Get all pvc Read get_replicaset_details Get detailed information about a specific ReplicaSet Read get_replicaset_events Get events related to a ReplicaSet Read get_replicaset_pods Get all pods managed by a ReplicaSet Read get_replicaset_rollout_status Get the rollout status of a ReplicaSet Read get_replicasets Get all replicasets Read get_service_accounts Get all service accounts in a namespace Read get_service_dependencies Get service dependencies and relationships Read get_service_details Get detailed information about a specific service Read get_service_endpoints Get endpoints for a service Read get_service_events Get events related to a service Read get_service_health Check the health of a service by making HTTP requests to its endpoints Read get_service_metrics Get metrics for a service (requires Prometheus) Read get_service_network_policy Get network policies affecting a service Read get_services Get all services Read get_statefulsets Get all statefulsets Read get_storageclasses Get all storageclasses

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 4 destructive tools including delete_deployment, delete_pod, delete_replicaset. 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 12 write tools including create_deployment, create_deployment_with_health_checks, create_deployment_with_resources. 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? +

65 tools across 4 categories: Destructive, Execute, Read, Write. 44 are read-only. 21 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 65 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.

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