Back
Marketplace/Kubernetes

TL;DR

Kubernetes is a Cloud Platforms MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent cluster operations — pods, deployments, services. Install in 1 minute with mcpizy install kubernetes.

☸️

Kubernetes

7 tools

Cloud Platforms

Last updated May 30, 2026 · By MCPizy team

Cluster operations — pods, deployments, services

Official homepage

Install Kubernetes

Via MCPizy CLI (recommended):
mcpizy install kubernetes
Or run directly:
npx -y mcp-server-kubernetes
View on GitHub

Tools exposed

7 tools available
list_pods

List pods in a namespace

Inputs

  • namespacestringoptional
describe_pod

Describe a pod with events and status

Inputs

  • namestringrequired
  • namespacestringoptional
get_logs

Fetch logs from a pod container

Inputs

  • namestringrequired
  • namespacestringoptional
list_deployments

List deployments in a namespace

Inputs

  • namespacestringoptional
scale_deployment

Scale a deployment to N replicas

Inputs

  • namestringrequired
  • replicasnumberrequired
  • namespacestringoptional
apply_manifest

Apply a YAML manifest

Inputs

  • manifeststringrequired
list_nodes

List all cluster nodes

Configuration

Works identically across clients. Only the config file path differs.

Claude Code~/.claude.json
{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": [
        "mcp-server-kubernetes"
      ]
    }
  }
}
Cursor.cursor/mcp.json
{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": [
        "mcp-server-kubernetes"
      ]
    }
  }
}
Windsurf~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "kubernetes": {
      "command": "npx",
      "args": [
        "mcp-server-kubernetes"
      ]
    }
  }
}

Authentication setup

  1. 1

    Ensure ~/.kube/config is set up and your current context points at the right cluster

    Get it KUBECONFIG

What you can do with Kubernetes MCP

Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.

“List every pod in the `production` namespace and show which ones are not Running”

Uses: list_pods

“Get the last 200 log lines from the `api-server` pod”

Uses: list_pods, get_logs

“Scale `web` deployment to 5 replicas in namespace `production`”

Uses: scale_deployment

“Describe the `payments-worker` pod and tell me why it keeps restarting”

Uses: describe_pod

Why Kubernetes MCP matters

Kubernetes MCP exposes the Kubernetes API as agent tools: `list_pods`, `get_pod_logs`, `describe_pod`, `list_deployments`, `scale_deployment`, `apply_manifest`, `exec_in_pod`, `get_events`. Authentication is whatever the kubeconfig provides — typically a service-account token or OIDC. Most MCP forks read `~/.kube/config` by default; for cluster-scoped agents in CI, mount a service-account token instead.

We use Kubernetes MCP for three workflows. First, pod-level triage: "why is the api deployment failing" — the agent walks `list_pods` → `describe_pod` → `get_pod_logs` → `get_events` and surfaces the root cause (image pull error, crashloop, OOMKilled). Second, manifest-driven changes: the agent edits a YAML, runs `apply_manifest`, and watches `get_events` for rollout status. Third, on-call response: scaled-down replica during off-hours, the agent identifies high CPU on the remaining pod and runs `scale_deployment` to bring more online. Token cost: `describe_pod` on a verbose pod (many events, conditions) is ~3-5k tokens; `get_pod_logs` is bounded by your `tail` parameter.

Compared to Docker MCP, Kubernetes is for cluster-scale (multi-node, declarative). Docker is for single-host. Compared to Bash MCP + kubectl, Kubernetes MCP wins on structured output and on safety (kubectl arguments are easy to typo into disasters; the MCP tools are tighter). Honest trade-off: Kubernetes is complex; the MCP exposes the surface but the agent still needs to understand pods, deployments, services, ingresses, namespaces. Without solid Kubernetes context in the system prompt, the agent will produce wrong manifests.

Common pitfalls

Cluster scope is broad — a service-account token with cluster-admin can delete any resource. Scope the SA with the smallest viable RBAC role.

`apply_manifest` with a malformed YAML often returns a vague error. The agent will sometimes retry with the same broken YAML. Pin a "validate before apply" step using `kubectl --dry-run=server` equivalent if the MCP supports it.

`get_pod_logs` on a multi-container pod requires a container name; without it, some MCPs default to the first container, others error. Always pass an explicit container.

Namespace defaults trip agents. The MCP's default namespace is whatever `current-context` says — agents that forget to pass `namespace` end up querying the wrong place. Pin the namespace in every call.

How Kubernetes MCP compares

Honest pros/cons against the closest cloud platforms MCP servers.

ServerStrengthsTrade-offs
Docker MCPSimpler, no cluster concepts, faster for dev workflowsSingle-host only, no orchestration
Helm MCP (community)Chart-level abstraction, easier for releasesSmaller surface, no raw kubectl ops
Bash MCP + kubectlFull kubectl surface, every flag availableShell injection, no structured output, typo-disaster risk

Works with

Claude Code
Claude Desktop
Cursor
Windsurf
VS Code + Copilot
Any MCP Client

More Cloud Platforms MCPs

🖥️

Proxmox

Manage VMs and containers via AI

🐋

Portainer

Container management via Portainer

☁️

Google Cloud Run

Deploy containerized applications to Google Cloud Run. Serverless container hosting.

🏗️

Terraform

Infrastructure as Code with HashiCorp Terraform

Alternatives to Kubernetes

If Kubernetes doesn't fit your stack, these Cloud Platforms MCP servers solve similar problems.

🟣

Pulumi

Cloud infrastructure with Pulumi Automation API

🏠

LocalStack

Local AWS for dev

☁️

Azure CLI

Execute Azure commands for cloud management

Key Takeaways

  • Kubernetes exposes 7 tools for cloud platforms workflows in Claude Code, Cursor and Windsurf.
  • Authentication: 1 step (KUBECONFIG).
  • Install in 1 command: mcpizy install kubernetes — config written to your client automatically.
  • Free and open source (GitHub source linked above) — verified compatible with every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + Copilot).
  • Best use case: "List every pod in the `production` namespace and show which ones are not Running".

Frequently asked questions

What is the Kubernetes MCP server?

The Kubernetes MCP server is an Cloud Platforms Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents cluster operations — pods, deployments, services. It exposes Kubernetes's capabilities as tools the AI can call directly from your editor or CLI.

How do I install Kubernetes MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install kubernetes` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y mcp-server-kubernetes` and restarting Claude Code.

Is Kubernetes MCP free?

Yes. The Kubernetes MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Kubernetes account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.

Does Kubernetes MCP work with Cursor and Windsurf?

Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.

What can I do with Kubernetes MCP?

Once installed, your AI agent can cluster operations — pods, deployments, services directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Kubernetes operations, inspect results, chain Kubernetes with other MCP servers (see our Workflow Recipes), and automate repetitive cloud platforms tasks without leaving your editor.

Manage all your MCPs in one place

Monitor usage, track costs, and discover new MCPs.

Get Started Free