Kubernetes MCP server (MKP)

MKP is a 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 keeps track of things like pods, deployments and services. If you work with a cluster and want to ask your AI questions about it, or have it make small changes, this is for you.

What this MCP server does

You ask your AI something about your cluster, like which pods are running or what a deployment looks like. Your AI sends that request to MKP, which talks directly to the Kubernetes API server for you. MKP fetches the answer, such as a list of resources, the details of one resource, or the logs from a pod. If write mode is turned on, it can also create or update resources, or run a command inside a pod. Then the result comes back into your chat in plain form.

Click to zoom

What you can do with it

• List the resources in your cluster, like pods, deployments and services
• Get the details or status of one specific resource
• Read the logs from a pod, including from a chosen container
• Create or update a resource from a manifest you provide
• Run a command inside a pod and see the output
• Filter lists by label or by which annotations to include
• Look up clustered resources like nodes

What it gives back to you

You get answers in your chat: lists of resources with their names and basic details, the full details of a single resource, or log lines from a pod. When it runs a command in a pod, you see the standard output and any error text. If it creates or updates something, it tells you what it applied.

Before you start

Who it's for

People who work with Kubernetes clusters, like developers, DevOps engineers and platform teams, who want to ask their AI about the cluster instead of typing commands by hand.