k8s-mcp-server — Kubernetes + Helm MCP Tools

Main

• Prefer --read-only for first runs; only enable write operations after you validate namespace scoping and auth paths.
• Use stdio mode for desktop clients and SSE/HTTP modes for web deployments; keep configs separate per environment.
• Keep kubeconfig and tokens out of agent prompts; pass them via env vars and mount paths as documented.

README excerpt (source)

# Kubernetes MCP Server

A Kubernetes Model Context Protocol (MCP) server that provides tools for interacting with Kubernetes clusters through a standardized interface.

## Hosted deployment

A hosted deployment is available on [Fronteir AI](https://fronteir.ai/mcp/reza-gholizade-k8s-mcp-server).

## Features

- **API Resource Discovery**: Get all available API resources in your Kubernetes cluster.
- **Resource Listing**: List resources of any type with optional namespace and label filtering.
- **Resource Details**: Get detailed information about specific Kubernetes resources.
- **Resource Description**: Get comprehensive descriptions of Kubernetes resources, similar to `kubectl describe`.
- **Pod Logs**: Retrieve logs from specific pods (optionally from a specific container, or all containers if unspecified).
- **Node Metrics**: Get resource usage metrics for specific nodes.
- **Pod Metrics**: Get CPU and Memory metrics for specific pods.
- **Event Listing**: List events within a namespace or for a specific resource.
- **Resource Creation/Updating**: Create new Kubernetes resources or update existing ones from a YAML or JSON manifest.

FAQ

Q: What modes are supported? A: The README documents stdio, SSE, and streamable-http modes with flags and env vars.

Q: Can I keep it read-only? A: Yes—use the --read-only flag as shown in the docs/config examples.

Q: How should I authenticate? A: Start with kubeconfig via env or mounted paths; avoid pasting tokens into chats.