// SCAN REPORT

Kubernetes MCP Server

81 tools. 22 can modify or destroy data without limits.

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

Last updated:

22 can modify or destroy data
59 read-only
81 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 (59) Write / Execute (20) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Kubernetes MCP Server tools

Destructive · Critical delete Deleting Kubernetes resources is an irreversible operation that can cause service outages, data loss, and infrastructure damage depending on what is deleted. Destructive · High helm-uninstall Uninstalling a Helm release removes all deployed resources, configurations, and potentially persistent data associated with that release. Execute · Critical exec The exec tool allows arbitrary command execution inside Kubernetes pod containers. Execute · High rollout-restart This tool triggers an external operation (Kubernetes rollout restart) whose effects depend on arguments (which deployment to restart).

22 of Kubernetes MCP Server's 81 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": {
    "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
{
  "annotate": {
    "limits": [
      {
        "counter": "annotate_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "analyze-resource-usage": {
    "limits": [
      {
        "counter": "analyze-resource-usage_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

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

Instant setup, no code required.

FULL CATALOGUE

All 81 Kubernetes MCP Server tools

DESTRUCTIVE 2 tools
Destructive delete Delete a Kubernetes resource Destructive helm-uninstall Uninstall a Helm release
EXECUTE 10 tools
Execute debug-pod Create a debug container in a pod Execute exec Execute a command in a pod container Execute helm-install Install a Helm chart Execute helm-upgrade Upgrade a Helm release Execute port-forward Port forward a Kubernetes service to a local port Execute port-forward-pod Port forward a Kubernetes pod to a local port Execute rollout-restart Restart a deployment by triggering a rollout Execute run Run a pod with a specific image Execute use-context Switch to a different kubectl context Execute wait Wait for a condition on a resource
WRITE 10 tools
Write annotate Add or update annotations on a resource Write apply Apply a Kubernetes manifest from a file or URL Write cp Copy files to/from a pod Write create-backup Create a backup of cluster resources Write create-ephemeral-container Create an ephemeral debug container in a pod Write create-namespace Create a new namespace Write label Add or update labels on a resource Write patch Patch a Kubernetes resource Write scale-deployment Scale a Kubernetes deployment to a specified number of replicas Write set-image Update the image of a deployment
READ 59 tools
Read analyze-resource-usage Analyze resource usage across the cluster Read api-resources Get available API resources Read api-versions Get available API versions Read argocd-app-status Get the status of an ArgoCD application Read argocd-list-apps List ArgoCD applications Read auth-can-i Check if the current user can perform an action Read cluster-info Get cluster information Read cordon-node Mark a node as unschedulable Read current-context Get the current kubectl context Read describe-configmap Describe details of a Kubernetes configmap Read describe-deployment Describe details of a Kubernetes deployment Read describe-node Describe details of a Kubernetes node Read describe-pod Describe details of a Kubernetes pod Read describe-secret Describe details of a Kubernetes secret Read describe-service Describe details of a Kubernetes service Read drain-node Drain a node for maintenance Read get-cluster-metrics Get cluster-wide metrics Read get-configmap Get the data from a configmap Read get-contexts List all kubectl contexts Read get-crd Get a custom resource definition Read get-events Get Kubernetes events for troubleshooting Read get-logs Get logs from a Kubernetes pod Read get-node-metrics Get detailed metrics for a node Read get-pod-metrics Get detailed metrics for a pod Read get-secret Get the data from a secret Read helm-list List Helm releases Read helm-status Get the status of a Helm release Read istio-list-gateways List Istio gateways Read istio-list-virtualservices List Istio virtual services Read list-all List all Kubernetes resources in a namespace Read list-clusterrolebindings List Kubernetes cluster role bindings Read list-clusterroles List Kubernetes cluster roles Read list-configmaps List Kubernetes configmaps in a namespace Read list-crds List Kubernetes custom resource definitions Read list-cronjobs List Kubernetes cronjobs in a namespace Read list-deployments List Kubernetes deployments in a namespace Read list-endpoints List Kubernetes endpoints in a namespace Read list-hpa List Kubernetes horizontal pod autoscalers in a namespace Read list-ingresses List Kubernetes ingresses in a namespace Read list-jobs List Kubernetes jobs in a namespace Read list-limitranges List Kubernetes limit ranges in a namespace Read list-namespaces List all Kubernetes namespaces Read list-networkpolicies List Kubernetes network policies in a namespace Read list-nodes List all Kubernetes nodes Read list-pods List Kubernetes pods in a namespace Read list-pv List Kubernetes persistent volumes Read list-pvc List Kubernetes persistent volume claims in a namespace Read list-resourcequotas List Kubernetes resource quotas in a namespace Read list-rolebindings List Kubernetes role bindings in a namespace Read list-roles List Kubernetes roles in a namespace Read list-secrets List Kubernetes secrets in a namespace Read list-serviceaccounts List Kubernetes service accounts in a namespace Read list-services List Kubernetes services in a namespace Read rollout-history Show the rollout history of a deployment Read rollout-status Check the rollout status of a deployment Read top-nodes Show resource usage for nodes Read top-pods Show resource usage for pods Read uncordon-node Mark a node as schedulable Read version Get Kubernetes version information
EXPLORE

Related servers

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

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
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 2 destructive tools including delete, helm-uninstall. 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 10 write tools including annotate, apply, cp. 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? +

81 tools across 4 categories: Destructive, Execute, Read, Write. 59 are read-only. 22 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 81 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.

81 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.