MCP server · Developer tools

Kubernetes MCP server

Lets your AI look inside a Kubernetes cluster to check pods, nodes, logs and warnings.

Developer tools For it and development For operations Cloud Platforms

This is a small helper that connects your AI assistant to a Kubernetes cluster. Kubernetes is the system many companies use to run their apps in the cloud, and it can be hard to see what is going wrong inside it. If your team runs apps on Kubernetes and you sometimes need to check what is broken, this is for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. 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 a Kubernetes cluster, so when you ask a question about your apps, the AI can actually go and look. You do not need to understand how it works inside; you just ask in plain words.

What this MCP server does

You ask your AI something like which pods are crashing. The AI passes that question to this helper. The helper talks to your Kubernetes cluster and reads the information it is allowed to see. Then the AI explains what it found in normal language. Everything it does is read-only, so it never changes or deletes anything in your cluster.

Flow diagram: you ask your AI “Which pods in my cluster are crashing?”, the Kubernetes MCP server connects it to Kubernetes cluster, and you get back plain answer in chat.

Click to zoom

What you can do with it

List the nodes in your cluster and see if they are healthy
Find pods that are crashing or stuck in a restart loop
Read the logs from a container to see error messages
List warning events like failed scheduling or failed mounts
Check ingress rules and TLS certificates for your web routes
Ask follow-up questions about what is broken and why

Try asking your AI

“Which pods in my cluster are crashing right now?”
“Show me the last 100 log lines from the payments pod”
“Are there any warning events in the last hour?”
“List all ingresses and tell me if any TLS certificate looks wrong”

What it gives back to you

You get back plain answers in the chat, often as short lists or summaries. For example, a list of pod names with their status, or the last lines of a log with the error highlighted. The AI can also explain what a warning event likely means. Nothing in your cluster is changed.

Before you start

What you need

Python 3.11 or newer installed on your computer
Access to a Kubernetes cluster (usually a kube config file)
Read-only permission on the cluster (your admin can set this up)
The Claude desktop app or another AI tool that supports MCP servers

Good to know

It is read-only by design and never touches secrets or config maps, but it can still read logs and cluster details, so only connect it to clusters you are allowed to inspect.

Install it with your AI

Add Kubernetes 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 Kubernetes 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.