k8s-mcp

What is this MCP

This is a read-only Model Context Protocol server specifically designed for Kubernetes clusters. It provides a comprehensive API to retrieve cluster information and diagnose issues, enabling AI assistants to understand and interact with Kubernetes environments.

How to use this MCP

The MCP server can be installed locally with Python 3.8+ and connected to a Kubernetes cluster via kubeconfig or in-cluster configuration. It integrates with Claude AI through a configuration file, allowing users to query cluster information via natural language prompts.

What this MCP can be used for

This MCP enables AI-assisted Kubernetes cluster management, including monitoring cluster health, debugging issues, inspecting resources, and managing deployments. It can answer questions about pods, nodes, services, and deployments, as well as help identify and troubleshoot common Kubernetes problems.