Complete AI Training

MCP server · Developer tools

Kom MCP server

by weibaohui

Lets your AI look at and manage your Kubernetes clusters, pods, and deployments for you.

Flow diagram: you ask your AI “Which pods are running in my clusters?”, the Kom MCP server reaches Cluster: production, Cluster: staging and Cluster: testing, and you get back plain answer in chat.

Kom is a helper that connects your AI assistant to Kubernetes, the system many companies use to run their apps on servers. Once it is set up, you can ask your AI things like which pods are running or restart a deployment, and it will go and do it. It is handy for anyone who works with servers or cloud apps but does not want to type long commands by hand.

What is an MCP server? The 30-second version

On its own, your AI can only chat. It cannot see your servers or change anything there. 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 when you ask a question about your clusters, the AI can go look things up or make changes for you.

What this MCP server does

You ask your AI a question about your Kubernetes setup, like which pods are running or why a deployment is stuck. The AI sends that request to this helper program. The helper talks to your Kubernetes clusters, gathers the information or makes the change you asked for, and sends the result back. Then the AI explains it to you in plain words in the chat. It can work with several clusters at once, so you can ask about any of them by name.

Flow diagram: you ask your AI “Which pods are running in my clusters?”, the Kom MCP server reaches Cluster: production, Cluster: staging and Cluster: testing, and you get back plain answer in chat. Click to zoom

What you can do with it

  • List all the Kubernetes clusters you have connected
  • List pods, deployments, nodes, and other resources in a cluster
  • Restart, stop, or scale a deployment up or down
  • Read the logs from a pod
  • Run a command inside a pod
  • Check node CPU and memory usage
  • Apply or delete resources using a YAML file

Try asking your AI

  • “List all pods in the kube-system namespace”
  • “Restart the nginx deployment in the default namespace”
  • “Show me the logs from the pod named web-1”
  • “Scale the api deployment to 5 replicas”

What it gives back to you

You get answers in the chat, usually as a list or a short summary. For example, it might show you a table of pods with their names and status, or tell you that a deployment was restarted. If you ask for logs, it shows the log text. If you ask it to change something, it tells you whether the change worked.

Before you start

What you need

  • A Kubernetes cluster you can reach
  • A kubeconfig file (a small file that holds the connection details for your cluster)
  • The kom program itself, either built from the source code or run as a binary

Good to know

This helper can change or delete things in your Kubernetes clusters, so be careful with requests that restart, scale, or remove resources.

Install it with your AI

Add Kom 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 Kom 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.

Sign in Become a member

Who it's for

Developers, DevOps engineers, and IT staff who manage Kubernetes clusters and want to ask questions or make changes using plain language.