Kubernetes MCP Server

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