K8m
๐๏ธ โ๏ธ/๐ - Provides MCP multi-cluster Kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources.
What is K8m?
K8m is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ๐๏ธ โ๏ธ/๐ - provides mcp multi-cluster kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common devops and development scenarios. s...
๐๏ธ โ๏ธ/๐ - Provides MCP multi-cluster Kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ๐๏ธ โ๏ธ/๐ - Provides MCP multi-cluster Kubernetes management a
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx k8mConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use K8m
K8m is an AI-driven Kubernetes dashboard and MCP server that provides multi-cluster management through a web UI and nearly 50 built-in MCP tools enabling 100+ cluster operations through tool combination. It supports both standard Kubernetes resources and Custom Resource Definitions (CRDs), integrates with local LLMs (Ollama, Qwen, DeepSeek) and cloud AI models for log analysis, YAML translation, and resource recommendations, and enforces role-based access control so each user's AI operations are bounded by their cluster permissions.
Prerequisites
- A running Kubernetes cluster with a valid kubeconfig file
- Docker or a Kubernetes deployment for running k8m itself
- An MCP-compatible client such as Claude Desktop or ChatGPT
- An LLM API key or local Ollama instance for AI features (optional but recommended)
Run k8m with Docker Compose
The fastest way to start k8m is with Docker Compose. Mount your kubeconfig and data volume, then access the dashboard at port 3618.
# docker-compose.yml
services:
k8m:
image: registry.cn-hangzhou.aliyuncs.com/minik8m/k8m
ports:
- "3618:3618"
volumes:
- ./data:/app/data
- ~/.kube/config:/root/.kube/configOr deploy directly to Kubernetes
Deploy k8m inside your cluster using the official manifest. It will be accessible via NodePort 31999.
kubectl apply -f https://raw.githubusercontent.com/weibaohui/k8m/refs/heads/main/deploy/k8m.yamlAccess the dashboard and log in
Navigate to http://127.0.0.1:3618 and log in with the default credentials. Change the password immediately in production.
# Default credentials:
# Username: k8m
# Password: k8m
# Access: http://127.0.0.1:3618Configure an AI model
In the dashboard settings, configure your preferred LLM for AI features: the built-in Qwen2.5-Coder-7B, a local Ollama instance, or a cloud API endpoint. This enables log analysis, YAML translation, and resource diagnostics.
Connect your MCP client
K8m exposes its 49 MCP tools via the MCP endpoint. Add it to your MCP client configuration with the k8m server URL.
K8m Examples
Client configuration
Claude Desktop configuration connecting to a running k8m MCP server.
{
"mcpServers": {
"k8m": {
"command": "npx",
"args": ["k8m"],
"env": {
"K8M_URL": "http://127.0.0.1:3618"
}
}
}
}Prompts to try
Example prompts for Kubernetes cluster management via k8m MCP tools.
- "List all pods in the production namespace and identify any that are not Running"
- "Analyze the logs from the payment-service pod and summarize any errors"
- "Scale the frontend deployment to 5 replicas"
- "What CRDs are installed in this cluster and which ones have active resources?"
- "Show resource usage across all nodes and recommend which pods to reschedule"Troubleshooting K8m
k8m cannot connect to the Kubernetes cluster
Ensure your kubeconfig is mounted correctly (for Docker) or that k8m has the appropriate RBAC permissions when running in-cluster. Check that --kubeconfig flag points to a valid, accessible config file.
AI features show no results or errors
Configure an LLM in the dashboard settings. If using Ollama, ensure the Ollama service is reachable from the k8m container/pod. Verify the model name matches exactly what Ollama has downloaded (e.g., qwen2.5-coder:7b).
MCP client cannot invoke k8m tools
Verify k8m is running and the MCP endpoint is accessible. Check the dashboard logs for MCP invocation errors. Ensure the user account used for MCP has sufficient RBAC permissions for the operations being requested.
Frequently Asked Questions about K8m
What is K8m?
K8m is a Model Context Protocol (MCP) server that ๐๏ธ โ๏ธ/๐ - provides mcp multi-cluster kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common devops and development scenarios. supports both standard and crd resources. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install K8m?
Follow the installation instructions on the K8m GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with K8m?
K8m works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is K8m free to use?
Yes, K8m is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
K8m Alternatives โ Similar Cloud Services Servers
Looking for alternatives to K8m? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
โ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
โ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
โ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
โ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
โ 26.7kๆฌ้กน็ฎไธบxiaozhi-esp32ๆไพๅ็ซฏๆๅก๏ผๅธฎๅฉๆจๅฟซ้ๆญๅปบESP32่ฎพๅคๆงๅถๆๅกๅจใBackend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
โ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up K8m in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use K8m?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.