Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
WindowsMacOS
Virtualization · Developer Tools
k8m
weibaohui/k8m
k8m is an AI-driven Mini Kubernetes AI Dashboard lightweight console tool designed to simplify cluster management.
Install
Client configuration
{
"mcpServers": {
"kom": {
"url": "http://IP:9096/sse"
}
}
}Environment variables
GIN_MODE- GitHub stars
- 234
- Author
- @weibaohui
- Category
- Virtualization, Developer Tools
- License
- MIT
- Updated
- Oct 6, 2026
About k8m
It is built on AMIS and uses kom as the Kubernetes API client. k8m comes with built-in Qwen2.5-Coder-7B, supports deepseek-ai/DeepSeek-R1-Distill-Qwen-7B model interaction capabilities, and supports integration with your own private AI models (including ollama).
k8m's design philosophy is "AI-driven, lightweight and efficient, simplifying complexity," helping developers and operators quickly get started and effortlessly manage Kubernetes clusters.
Features
Miniaturized Design: All functionalities are integrated into a single executable file for easy deployment and simple usage.
Easy to Use: Friendly user interface and intuitive operation workflow make Kubernetes management easier. Supports standard k8s, aws eks, k3s, kind, k0s and other cluster types.
High Performance: Backend built with Golang, frontend based on Baidu AMIS, ensuring high resource utilization and fast response speed.
AI-Driven Integration: Implements word explanation, resource guide, YAML attribute automatic translation, Describe information interpretation, log AI diagnosis, and running command recommendation…
Feature Plugin: Feature functions are plugin-based, enabled on demand, no resource consumption when not enabled.
MCP Integration: Visual management of MCP, enabling large model calls to Tools, with 49 built-in k8s multi-cluster MCP tools that can be combined to achieve over a hundred cluster operations. Can…
MCP Permission Integration: Multi-cluster management permissions and MCP large model call permissions are integrated. In a nutshell: whoever uses the large model executes MCP with their permissions.…
Multi-Cluster Management: Automatically recognizes clusters using InCluster mode internally, automatically scans configuration files in the same directory after configuring kubeconfig path, and…
Multi-Cluster Permission Management: Supports authorization for users and user groups, can authorize by cluster, including cluster read-only, Exec command, and cluster administrator three types of…
Supports k8s Latest Features: Supports APIGateway, OpenKruise and other functional features.
Details on this page are taken from the project's README. Open README
Supported clients
Clients mentioned in this server's README:
Cursor
Desktop · Freemium · Proprietary
The first agentic IDE. The Cursor editor truly merges how developers and AI work together, delivering a magical coding experience.
Windsurf
Desktop · Freemium · Proprietary
The first agentic IDE. The Windsurf editor truly merges how developers and AI work together.
Related MCP servers
MCP Jetbrains
JetBrains/mcp-jetbrains
Issues & Support: For bugs or feature requests related to the built-in MCP functionality, please use the JetBrains YouTrack.
Docker Compose
ckreiling/mcp-server-docker
An MCP server for managing Docker with natural language!
Docker MCP
QuantGeekDev/docker-mcp
A powerful Model Context Protocol (MCP) server for Docker operations, enabling seamless container and compose stack management through Claude AI.
Code Sandbox MCP
Automata-Labs-team/code-sandbox-mcp
A secure sandbox environment for executing code within Docker containers. This MCP server provides AI applications with a safe and isolated environment for running code while maintaining security through containerization.
Proxmox MCP Server
canvrno/ProxmoxMCP
A Python-based Model Context Protocol (MCP) server for interacting with Proxmox hypervisors, providing a clean interface for managing nodes, VMs, and containers.
Dynamic MCP Server Creator
tesla0225/mcp-create
A dynamic MCP server management service that creates, runs, and manages Model Context Protocol (MCP) servers dynamically. This service itself functions as an MCP server and launches/manages other MCP servers as child processes, enabling a flexible MCP ecosystem.