MCP.so
登录

Kubernetes MCP Server

@manusa

关于 Kubernetes MCP Server

Model Context Protocol (MCP) server for Kubernetes and OpenShift

基本信息

分类

云与基础设施

许可证

Apache-2.0

运行时

go

传输方式

stdio

发布者

manusa

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "kubernetes-mcp-server": {
      "command": "npx",
      "args": [
        "kubernetes-mcp-server@latest",
        "--help"
      ]
    }
  }
}

工具

21

List all available context names and associated server urls from the kubeconfig file

List all available targets

Get the current Kubernetes configuration content as a kubeconfig YAML

List Kubernetes events (warnings, errors, state changes) for debugging and troubleshooting in the current cluster from all namespaces

List all the Kubernetes namespaces in the current cluster

List all the OpenShift projects in the current cluster

Get logs from a Kubernetes node (kubelet, kube-proxy, or other system logs). This accesses node logs through the Kubernetes API proxy to the kubelet

Get detailed resource usage statistics from a Kubernetes node via the kubelet's Summary API. Provides comprehensive metrics including CPU, memory, filesystem, and network usage at the node, pod, and container levels. On systems with cgroup v2 and kernel 4.20+, also includes PSI (Pressure Stall Information) metrics that show resource pressure for CPU, memory, and I/O. See https://kubernetes.io/docs/reference/instrumentation/understand-psi-metrics/ for details on PSI metrics

List the resource consumption (CPU and memory) as recorded by the Kubernetes Metrics Server for the specified Kubernetes Nodes or all nodes in the cluster

List all the Kubernetes pods in the current cluster from all namespaces

List all the Kubernetes pods in the specified namespace in the current cluster

Get a Kubernetes Pod in the current or provided namespace with the provided name

Delete a Kubernetes Pod in the current or provided namespace with the provided name

List the resource consumption (CPU and memory) as recorded by the Kubernetes Metrics Server for the specified Kubernetes Pods in the all namespaces, the provided namespace, or the current namespace

Execute a command in a Kubernetes Pod (shell access, run commands in container) in the current or provided namespace with the provided name and command

Get the logs of a Kubernetes Pod in the current or provided namespace with the provided name

Run a Kubernetes Pod in the current or provided namespace with the provided container image and optional name

List Kubernetes resources and objects in the current cluster by providing their apiVersion and kind and optionally the namespace and label selector

Get a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name

Create or update a Kubernetes resource via Server-Side Apply. The manifest is the complete desired state: any field this tool previously set and the new manifest omits is removed. To edit an existing resource, fetch it with resources_get, modify it, then re-apply the full resource.

Delete a Kubernetes resource in the current cluster by providing its apiVersion, kind, optionally the namespace, and its name

概览

What is Kubernetes MCP Server?

A Go-based native implementation of the Model Context Protocol for Kubernetes and OpenShift that interacts directly with the Kubernetes API server without external command-line tools. It provides tools for managing Kubernetes resources, pods, namespaces, events, projects, Helm releases, and Tekton pipelines. Designed for AI agents and developer tools like Claude Desktop, VS Code, and Cursor.

How to use Kubernetes MCP Server?

Install via npm, PyPI, or download the native binary for Linux, macOS, or Windows. Configure using command-line arguments, TOML files, or environment variables. Add the server to your MCP client’s configuration (e.g., Claude Desktop, VS Code, Cursor) by specifying the command and arguments (e.g., npx -y kubernetes-mcp-server@latest). The server automatically detects changes in your Kubernetes kubeconfig.

Key features of Kubernetes MCP Server

  • Native Go implementation, no kubectl or helm required.
  • Automatically detects Kubernetes configuration changes.
  • Full CRUD operations on any Kubernetes or OpenShift resource.
  • Pod-specific operations: list, get, delete, logs, top, exec, run.
  • Helm chart install, list, uninstall.
  • Tekton pipeline and task management.
  • Optional OpenTelemetry distributed tracing and metrics.

Use cases of Kubernetes MCP Server

  • Diagnose and automatically fix OpenShift deployments using Claude Desktop.
  • Vibe code and deploy a game to OpenShift with AI assistance.
  • Supercharge GitHub Copilot with Kubernetes management in VS Code.
  • Manage multiple Kubernetes clusters from a single MCP client.
  • Interact with Kubernetes resources through natural language commands.

FAQ from Kubernetes MCP Server

How is this different from other Kubernetes MCP servers?

This server is a Go-based native implementation that directly communicates with the Kubernetes API server, not a wrapper around kubectl or helm. It requires no external dependencies.

What are the prerequisites to use this server?

You need access to a Kubernetes cluster. The server can use your existing kubeconfig or in-cluster configuration.

Can

评论

云与基础设施 分类下的更多 MCP 服务器