← Leaderboard

Kubernetes MCP Server

Partner — verifiedlocal

MCP server for interacting with Kubernetes clusters via kubectl

Unknown author · joined 2026-08-11

View in directory
Popularity rank
#760

of 2,090

Popularity score
9,625

directory metric

Trending rank

no score

Tools
22

exposed by this server

Movement

Rank, 24h

Rank, 7d

Score, 24h

Score, 7d

30-day trend

Movement is measured against our own daily snapshots, which begin the day this site launched. Nothing to compare against yet.

About

MCP Server that can connect to a Kubernetes cluster and manage it.

By default, the server loads kubeconfig from `~/.kube/config`.

The server will automatically connect to your current kubectl context. Make sure you have:

1. kubectl installed and in your PATH 2. A valid kubeconfig file with contexts configured 3. Access to a Kubernetes cluster configured for kubectl (e.g. minikube, Rancher Desktop, GKE, etc.) 4. Optional: Helm v3 installed and in your PATH.

You can verify your connection by asking Claude to list your pods or create a test deployment.

If you have errors open up a standard terminal and run `kubectl get pods` to see if you can connect to your cluster without credentials issues.

## Features

  • [x] Connect to a Kubernetes cluster
  • [x] Unified kubectl API for managing resources
  • Get or list resources with `kubectl_get`
  • Describe resources with `kubectl_describe`
  • List resources with `kubectl_get`
  • Create resources with `kubectl_create`
  • Apply YAML manifests with `kubectl_apply`
  • Delete resources with `kubectl_delete`
  • Get logs with `kubectl_logs`
  • and more.

Connection

Works with
claude-desktop

Tools 22

  • ping
  • cleanup
  • kubectl_get
  • kubectl_describe
  • kubectl_apply
  • kubectl_delete
  • kubectl_create
  • kubectl_logs
  • kubectl_patch
  • kubectl_rollout
  • kubectl_scale
  • kubectl_context
  • kubectl_generic
  • install_helm_chart
  • upgrade_helm_chart
  • uninstall_helm_chart
  • explain_resource
  • list_api_resources
  • node_management
  • exec_in_pod
  • port_forward
  • stop_port_forward