MCP server · Developer tools

Kubernetes MCP server (k8s-aiops)

Lets your AI look at and manage your Kubernetes clusters, with every action logged and reversible.

Developer tools For it and development For operations Cloud Platforms

This is a helper that connects your AI assistant to a Kubernetes cluster, the system many companies use to run their apps in the cloud. Once it is set up, you can ask your AI to list pods, check why something is broken, or restart a deployment, and it will actually do it. It is handy for anyone who works with cloud apps but does not want to memorize long command lines.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to another system. This one connects your AI to Kubernetes, so the AI can look things up or make changes there when you ask. You stay in charge: the AI just uses this helper to talk to your cluster.

What this MCP server does

You ask your AI something like "what is broken in my prod namespace?" The AI sends that request to this helper program. The helper talks to your Kubernetes cluster using your existing login settings. It brings back the answer, like a list of unhealthy pods or a summary of what went wrong. Every action it takes is written to a local log file on your computer, so you can see what happened later.

Flow diagram: you ask your AI “What is broken in my prod namespace?”, on your own computer the Kubernetes MCP server (k8s-aiops) works with your Kubernetes cluster, and you get back plain answers in chat.

Click to zoom

What you can do with it

List pods, deployments, services, and other things running in your cluster
Diagnose why a pod or workload is unhealthy, with the worst problem shown first
Restart or scale a deployment up or down
Check rollout status, history, and undo a bad rollout
Look at nodes, namespaces, events, and storage volumes
Preview a change with a dry run before it actually happens
See secret names and keys, but not the secret values themselves

Try asking your AI

“Show me all the pods in the prod namespace that are not running”
“Why is my checkout deployment failing to start?”
“Restart the payments deployment in staging”
“Give me a health summary of my cluster”

What it gives back to you

You get back plain answers in the chat: lists of pods or deployments, a health summary, or an explanation of what is wrong and why. If you asked for a change, it tells you what it did, and for reversible actions it remembers how to undo it. Every call is also quietly recorded in a local log file on your machine.

Before you start

What you need

A Kubernetes cluster you can reach, and a kubeconfig file that already lets you log in to it
The uv tool installed (a small program that runs Python tools)
The k8s-aiops tool installed, or the Claude Code or OpenClaw plugin
Your kubeconfig path if it is not in the usual place

Good to know

It can change or delete things in your cluster, so only connect it with a kubeconfig that has the permissions you are comfortable giving it, and use dry runs when you are unsure.

Install it with your AI

Add Kubernetes MCP server (k8s-aiops) to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Kubernetes MCP server (k8s-aiops), install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.