Mmcp.market

Kubeview MCP server

by mikhae1·io.github.mikhae1/kubeview·v2.0.1
No reviews yet

Read-only Model Context Protocol MCP server enabling code-driven AI analysis of Kubernetes clusters.

B75/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
Growing

5 stars299 downloads/wk

Reviews

Write one

Nobody has reviewed Kubeview yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Kubeview tools (52, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • argo_cron_list

    List Argo cron workflows in the cluster (similar to `argo cron list`)

  • argo_get

    Get details of an Argo workflow (similar to `argo get <workflow-name>`)

  • argo_list

    List Argo Workflows (similar to `argo list`). Supports filters: namespace/all-namespaces, selector, status (running|succeeded|failed|pending|completed), since, and limits.

  • argo_logs

    Get logs from Argo workflow pods (similar to `argo logs`)

  • argocd_app

    Get Argo CD applications data (similar to `argocd app`): list|get|resources|logs|history|status.

  • argocd_app_get

    Get details of an ArgoCD application (similar to `argocd app get <app-name>`)

  • argocd_app_history

    Get deployment history/revisions of an ArgoCD application (similar to `argocd app history <app-name>`)

  • argocd_app_list

    List ArgoCD applications in the cluster (similar to `argocd app list`)

  • argocd_app_resources

    List resources of an ArgoCD application (similar to `argocd app resources <app-name>`)

  • get_configmaps

    List all ConfigMap resources in the current Kubernetes cluster (similar to `kubectl get configmap`)

  • get_cronjobs

    List CronJob resources with status, last run, schedule, and failures

  • get_daemonsets

    List DaemonSet resources with status and rollout health

  • get_deployments

    List all Deployment resources in the current Kubernetes cluster (similar to `kubectl get deployments`)

  • get_endpoints

    List Endpoints with ready vs not-ready addresses for Service backends

  • get_endpointslices

    List EndpointSlices showing ready vs not-ready endpoints and topology

  • get_events

    Show events in the Kubernetes cluster (similar to `kubectl get events`)

  • get_hpa

    List HorizontalPodAutoscalers with targets, current/desired replicas, and metrics

  • get_ingresses

    List Ingress resources in the current Kubernetes cluster (similar to `kubectl get ingress`)

  • get_jobs

    List Job resources with status, last run, failures, backoff reasons

  • get_limitranges

    List LimitRanges with default requests/limits and max/min values

  • get_metrics

    Fetch live CPU / memory metrics for all nodes and pods in the current cluster (similar to `kubectl top`), with optional enrichment from Prometheus data.

  • get_namespaces

    List all Namespace resources in the current Kubernetes cluster (similar to `kubectl get namespaces`)

  • get_nodes

    List Node resources with conditions, capacity/allocatable, taints, and pressure flags

  • get_pdb

    List PodDisruptionBudgets with status and disruptions allowed

  • get_persistent_volume_claims

    List Persistent Volume Claim resources in the current Kubernetes cluster and optionally analyze their status (similar to `kubectl get pvc`)

  • get_persistent_volumes

    List all Persistent Volume resources in the current Kubernetes cluster and optionally analyze their status (similar to `kubectl get pv`)

  • get_pod_metrics

    Fetch CPU and memory metrics for pods in the current Kubernetes cluster (similar to `kubectl top pods`)

  • get_pods

    List Pod resources in the current Kubernetes cluster (similar to `kubectl get pods`)

  • get_replicasets

    List ReplicaSet resources with status and rollout health

  • get_resourcequotas

    List ResourceQuotas with current usage and hard limits

  • get_secrets

    List all Secret resources in the current Kubernetes cluster (similar to `kubectl get secrets`)

  • get_services

    List Service resources in the current Kubernetes cluster (similar to `kubectl get svc`)

  • get_statefulsets

    List StatefulSet resources with status and rollout health

  • helm_debug

    Debug a Helm release by combining stored release data, live Kubernetes resource state, workload readiness, and correlated warning events.

  • helm_get

    Get Helm release data: values, manifest, notes, hooks, resources, status, or history.

  • helm_get_hooks

    Get the hooks for a named release (similar to `helm get hooks`)

  • helm_get_manifest

    Get the manifest for a named release (similar to `helm get manifest`)

  • helm_get_notes

    Get the notes for a named release (similar to `helm get notes`)

  • helm_get_resources

    Get Kubernetes resources created by a Helm release with resource analysis

  • helm_get_values

    Get the values file for a named release (similar to `helm get values`)

  • helm_history

    Fetch release history for a given release (similar to `helm history`)

  • helm_list

    List Helm releases in the cluster.

  • helm_list_with_resources

    List Helm releases with detailed Kubernetes resource breakdown

  • helm_status

    Display the status of the named release (similar to `helm status`)

  • kube_get

    Get a specific Kubernetes resource directly from the API (close to kubectl describe). Supports any resource (core, built-in, or CRD) via kind/plural or group/version/resource, and provides structured details with optional events and diagnostics. Also supports listing when no name is provided.

  • kube_list

    List Kubernetes resources by type with common selectors (supports: [pod, service, deployment, node, role, clusterrole, rolebinding, clusterrolebinding, replicaset, statefulset, daemonset, job, cronjob, hpa, pdb, endpoints, endpointslice, resourcequota, limitrange, namespace, persistentvolume, persistentvolumeclaim, secret, configmap]). If resourceType is omitted, returns a consolidated cluster ove

  • kube_logs

    Tail logs from multiple pods/containers with dynamic discovery, filters, and merged Kubernetes events.

  • kube_metrics

    One-shot cluster metrics and diagnostics. By default returns node and workload (pods) CPU/memory plus a summary and detected problems. Supports optional focus on nodes or pods, namespace scoping, and Prometheus enrichment.

  • kube_net

    Network diagnostics from a source pod: DNS resolution, internet egress, and pod/service connectivity checks with robust fallbacks.

  • kube_pod_execwrite action

    Execute a command in a container of a pod via the Kubernetes API (no kubectl). Captures stdout/stderr and returns them when the command completes.

  • kube_port_forward

    Temporary port-forward to a pod/service for local probing (runs with a timeout).

  • sample-echo

    A sample tool that echoes back the input

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

1 medium
  • Code scan378 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 18 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/src/agent/runtime/ivm/IVMSandboxManager.js: …soleBridge); await this.context.eval(` (() => { const bridg…
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Kubeview repository's README, as published. We do not edit it. Read it on GitHub

KubeView MCP

Read-only Model Context Protocol server for Kubernetes diagnostics. Instead of exposing dozens of tools, it gives the agent a sandboxed TypeScript runtime: a single run_code call can query Kubernetes, Helm, Argo Workflows, and Argo CD, correlate the results, and return only the answer. Intermediate payloads never pass through the model's context window. Based on the code execution with MCP pattern.

Background: Evicting MCP tool calls from your Kubernetes cluster

How it works

v2 publishes exactly two public tools: runcode and an approval-gated kubepod_exec. Everything else is discovered inside the sandbox via tools.list(), tools.search(), and tools.help(), following the MCP progressive discovery and programmatic calling guidance.

run_code executes bounded TypeScript with top-level await. One call can list workloads, correlate events, fetch logs, and diff Helm state without shipping intermediate payloads back through the model:

const pods = await tools.kubernetes.list({ namespace: 'payments' });
const unhealthy = pods.items.filter((p) => p.status?.phase !== 'Running');

return Promise.all(
  unhealthy.map(async (pod) => ({
    pod: pod.metadata?.name,
    logs: await tools.kubernetes.logs({
      namespace: 'payments',
      podName: pod.metadata?.name,
      tailLines: 100,
    }),
  })),
);
  • Sensitive isolation — kubepodexec is unreachable from sandboxed code. Top-level exec requires MCP elicitation, is bound to the argument digest, expires after 10 minutes, and fails closed. kubeportforward is never a top-level tool and is denied inside code mode by default. tools.disabled() reports which policy blocked a capability and whether that denial is configurable.
  • API-driven discovery — Argo Workflows and Argo CD are detected from the Kubernetes API, scoped to the active kube context, cached for 60 s. An unavailable optional API never blocks startup.
  • Native reads — resources, metrics, logs, events, and network probes go through the Kubernetes API. Helm releases are parsed from cluster Secrets or ConfigMaps; a local helm binary is a fallback, not a prerequisite.

Quick start

Prerequisites: Node.js ≥ 22 and access to a cluster (KUBECONFIG or in-cluster service account).

npx -y kubeview-mcp

# Claude Code
claude mcp add kubernetes -- npx kubeview-mcp
{
  "mcpServers": {
    "kubeview": {
      "command": "npx",
      "args": ["-y", "kubeview-mcp"]
    }
  }
}

In Cursor, /kubeview/code-mode injects the typed API into context.

Configuration

Cluster

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

Runs npx -y kubeview-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add kubeview -- npx -y kubeview-mcp
Add to Cursor

Kubeview: common questions

Is Kubeview MCP server safe?
Mostly: it is graded B (75/100). Read the Kubeview safety report
How do I install Kubeview?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Kubeview need an API key?
Yes. The registry entry asks for MCP_APPROVAL_STATE_SECRET.
Is Kubeview maintained?
The last commit was 19 days ago (2026-09-02). The latest release is v2.0.1.
What can I use instead of Kubeview?
Servers from other publishers that do the same job: Ocm MCP server, KSail MCP server and Kubernetes MCP server. Compare all Kubeview alternatives.

Alternatives to Kubeview

Same job from other publishers: the closest match first, then the best rated.

All Kubeview alternatives →
  • Ocm
    Guardrailed fleet ops for AI agents: multi-cluster Kubernetes via OCM with policy, approval, audit.
    B
  • KSail
    SDK for creating, managing, and operating Kubernetes clusters and workloads with ease.
    A
  • Kubernetes
    A Model Context Protocol (MCP) server for Kubernetes and OpenShift
    A
  • Radar Kubernetes MCP Server
    Kubernetes MCP server for diagnosis, resource management, GitOps, and RBAC-enforced operations.
    A
  • VMware AVI
    VMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 28 MCP tools.
    A
Kubeview vs OcmKubeview vs KSailKubeview vs Kubernetes

More from mikhae1 →