K8s MCP Server

Created By

christian-schlichtherle4 months ago

An MCP server for comprehensive access to one or more Kubernetes clusters

Overview

What is K8s MCP Server?

K8s MCP Server is a tool designed to provide comprehensive access to one or more Kubernetes clusters, enhancing Kubernetes management with AI-friendly port-forward management and supporting headless services.

How to use K8s MCP Server?

To use K8s MCP Server, install the required dependencies, set the necessary environment variables for Kubernetes configurations, and run the server using Python.

Key features of K8s MCP Server?

kubectl-Inspired Output Formats: Supports multiple output formats for efficient token usage.
Resource Kind Discovery: Allows natural language queries to find resources by keywords.
URL-based Configuration: Enables sharing of port-forward configurations via GitHub Gists or local files.
Headless Service Support: Facilitates direct pod targeting via label selectors.
AI-Optimized: Features a clean service/target structure for intelligent fuzzy matching.
Session Management: Tracks in-memory port-forward sessions with capabilities to list and teardown.

Use cases of K8s MCP Server?

Setting up port-forwarding to specific services in a Kubernetes cluster.
Discovering available resources and their configurations in a cluster.
Managing multiple Kubernetes clusters efficiently with AI assistance.

FAQ from K8s MCP Server?

Can K8s MCP Server manage multiple clusters?

Yes! It is designed to provide access to one or more Kubernetes clusters.

Is K8s MCP Server easy to set up?

Yes! Follow the quick start guide to install dependencies and configure the environment.

What programming language is K8s MCP Server written in?

K8s MCP Server is implemented in Python.

Server Config

{
  "mcpServers": {
    "k8s": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/k8s-mcp",
        "run",
        "k8s-mcp"
      ],
      "env": {
        "KUBECONFIG_ALIASES": "development=dev production=prod",
        "KUBECONFIG_URLS": "dev=file:///path/to/development/k3s/kubeconfig.yaml prod=file:///path/to/production/k3s/kubeconfig.yaml",
        "PORT_FORWARD_CONFIG_URL": "file:///path/to/k8s-mcp/port-forward-config.yaml"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

DeepChatYour AI Partner on Desktop

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

Playwright McpPlaywright MCP server

ChatWiseThe second fastest AI chatbot™

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

CursorThe AI Code Editor

TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Serper MCP ServerA Serper MCP Server

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.