MCP Kubernetes
An MCP server that enables AI assistants to interact with Kubernetes clusters by translating natural language into kubectl and Helm operations. It allows users to query, manage, and diagnose Kubernetes resources and cluster states through a seamless
What is MCP Kubernetes?
MCP Kubernetes is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables ai assistants to interact with kubernetes clusters by translating natural language into kubectl and helm operations. it allows users to query, manage, and diagnose kubernetes r...
An MCP server that enables AI assistants to interact with Kubernetes clusters by translating natural language into kubectl and Helm operations. It allows users to query, manage, and diagnose Kubernetes resources and cluster states through a seamless
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- kubectl
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp-kubernetes-serverManual Installation
npx -y mcp-kubernetes-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Kubernetes
mcp-kubernetes-server is an MCP server written in Go that bridges AI assistants with live Kubernetes clusters, translating natural language into kubectl and Helm operations. It exposes over 40 tools covering cluster inspection, resource management, log retrieval, rollout control, scaling, autoscaling, and node management, making it possible to diagnose pod failures, deploy workloads, or query cluster state entirely through conversational prompts. Engineers use it to accelerate Kubernetes troubleshooting and automation without switching to a terminal.
Prerequisites
- A running Kubernetes cluster with a valid kubeconfig file (~/.kube/config or custom path)
- kubectl installed and working on the host machine
- helm installed on the host machine (required for Helm tools)
- Docker installed if using the container-based setup
- An MCP-compatible client such as Claude Desktop or Cursor
Choose your installation method
The server supports three installation methods: Docker (recommended for isolation), uvx (Python runner, no global install), and local development. Docker is easiest if you already have it installed.
Option A: Configure with Docker
Mount your kubeconfig file into the container. Replace /home/username with your actual home directory path.
{
"mcpServers": {
"kubernetes": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"--mount", "type=bind,src=/home/username/.kube/config,dst=/home/mcp/.kube/config",
"ghcr.io/feiskyer/mcp-kubernetes-server"
]
}
}
}Option B: Configure with uvx
Install the uv package manager first, then configure the MCP client to run the server via uvx with your KUBECONFIG path.
# Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
# Then use this config:
{
"mcpServers": {
"kubernetes": {
"command": "uvx",
"args": ["mcp-kubernetes-server"],
"env": {
"KUBECONFIG": "/home/you/.kube/config"
}
}
}
}Add the configuration to Claude Desktop
Open ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows) and paste the chosen config block into the mcpServers object.
Restart Claude Desktop and verify cluster access
Restart Claude Desktop. Ask 'What nodes are in my Kubernetes cluster?' to confirm connectivity. The server will execute kubectl commands against your configured cluster.
MCP Kubernetes Examples
Client configuration (Docker method)
Complete claude_desktop_config.json for mcp-kubernetes-server using Docker to mount the kubeconfig.
{
"mcpServers": {
"kubernetes": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"--mount", "type=bind,src=/home/username/.kube/config,dst=/home/mcp/.kube/config",
"ghcr.io/feiskyer/mcp-kubernetes-server"
]
}
}
}Prompts to try
Natural language prompts that the server translates into kubectl and Helm operations.
- "What is the status of all pods in the default namespace?"
- "Why is my nginx deployment failing? Show me the pod logs."
- "Scale the api-server deployment to 5 replicas."
- "List all nodes and their current CPU and memory usage."
- "Roll back the frontend deployment to the previous revision."
- "Show me all events in the kube-system namespace from the last 10 minutes."Troubleshooting MCP Kubernetes
Server errors with 'kubeconfig not found' or cannot connect to cluster
Verify the KUBECONFIG path is correct and the file exists. For Docker, confirm the bind mount source path (src=) matches the actual location of your config file. Run 'kubectl cluster-info' in a terminal to confirm the config works outside the server.
Helm commands fail with 'helm not found'
Install helm on the host machine (https://helm.sh/docs/intro/install/) and ensure it is on your PATH. For Docker installations, the container image includes helm — no host-level helm required.
Write operations (create, delete, scale) are blocked
Check if the server was started with --disable-write or --disable-delete flags. Remove those flags from the args array in your MCP client configuration, then restart Claude Desktop.
Frequently Asked Questions about MCP Kubernetes
What is MCP Kubernetes?
MCP Kubernetes is a Model Context Protocol (MCP) server that mcp server that enables ai assistants to interact with kubernetes clusters by translating natural language into kubectl and helm operations. it allows users to query, manage, and diagnose kubernetes resources and cluster states through a seamless It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Kubernetes?
Install via npm with the command: npx -y mcp-kubernetes-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with MCP Kubernetes?
MCP Kubernetes works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Kubernetes free to use?
Yes, MCP Kubernetes is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
MCP Kubernetes Alternatives — Similar Cloud Services Servers
Looking for alternatives to MCP Kubernetes? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 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 MCP Kubernetes 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 MCP Kubernetes?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.