MCP server · Developer tools

K8M MCP server

Let your AI look after your Kubernetes clusters: check pods, read logs, and run common tasks for you.

Developer tools For it and development For operations Cloud Platforms

K8M is a small control panel for Kubernetes, the system many companies use to run their apps in the cloud. It also acts as an MCP server, which means your AI assistant can connect to it and help you manage your clusters. It is handy if you work with Kubernetes but are not a full time engineer, or if you just want a simpler way to check what is going on.

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 app. Here, that helper connects your AI to K8M and the Kubernetes clusters it manages, so the AI can look things up or carry out tasks there when you ask. You stay in control: the AI uses your own permissions, so it can only do what you are allowed to do.

What this MCP server does

You ask your AI a question about your clusters, like which pods are failing. The AI sends that request to the K8M MCP server. The server talks to your Kubernetes clusters through K8M and gathers the answer. Then it sends the result back, and the AI explains it to you in the chat. K8M also keeps a record of every MCP call, so you can see what was asked and what happened.

Flow diagram: you ask your AI “Which pods are failing in production right now?”, the K8M MCP server connects it to Kubernetes clusters, and you get back plain answers in chat.

Click to zoom

What you can do with it

List the clusters, namespaces, and pods you manage
Read logs from a pod to find errors
Describe a resource to see its status and events
Run common Kubernetes tasks like restarting or scaling a workload
Look up custom resources (CRDs) in your clusters
Check cluster health and recent events
Use your own permissions, so you cannot do more than you are allowed

Try asking your AI

“Which pods are failing in the production cluster right now?”
“Show me the last 50 lines of logs from the checkout service pod”
“Restart the deployment called web-frontend in the staging namespace”
“What events happened in the payments namespace in the last hour?”

What it gives back to you

You get answers in plain chat: lists of clusters, namespaces, pods, or resources, short summaries of what is wrong, log excerpts, and the result of any action the AI took. For example, it might say that two pods are in a crash loop and show the last error lines. If it changed something, it tells you what it did. Everything stays in the conversation, so you can ask follow up questions.

Before you start

What you need

A running K8M instance (you can download it from GitHub or run it with Docker)
Access to at least one Kubernetes cluster, with a kubeconfig file or in-cluster setup
Your K8M login (the default is k8m / k8m, but change it right away)
An AI app that supports MCP, like Claude Desktop or another tool that can add MCP servers

Good to know

The AI can change or delete things in your clusters, so check before letting it run actions like restarting or scaling workloads.

Install it with your AI

Add K8M MCP server 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 K8M MCP server, 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.