Kubernetes MCP server

This is a helper that connects your AI assistant to a Kubernetes cluster. Kubernetes is the system many companies use to run their apps in containers, and it can be hard to see what is going on inside it. If you work near a cluster and want to ask questions about it in plain words, this server is for you.

What this MCP server does

You ask your AI something about your cluster, like which pods are running or why one is failing. The AI sends that request to this helper program. The helper talks to your Kubernetes cluster using your existing access settings. It brings back the answer, such as a list of resources, the logs from a pod, or the CPU and memory numbers for a node. If write access is on, it can also create, update, or delete resources for you from a file you provide.

Click to zoom

What you can do with it

• List the resources in your cluster, filtered by namespace or labels
• Read the logs from a specific pod or container
• Check CPU and memory metrics for pods and nodes
• Describe a resource in detail, like kubectl describe does
• List recent events in a namespace or for one resource
• Create or update a resource from a YAML or JSON file
• Delete a resource when you ask it to

Try asking your AI

• “List all pods in the default namespace and tell me which ones are not running”
• “Show me the logs from the pod called web-7f9c in the staging namespace”
• “What are the CPU and memory numbers for the node worker-2”
• “Are there any warning events in the production namespace in the last hour”

What it gives back to you

You get answers in the chat, in plain words. That can be a list of resources, a summary of a pod's state, the raw log lines from a container, or numbers for CPU and memory. If you asked it to change something, it tells you what it created, updated, or deleted.

Before you start

Who it's for

Developers, DevOps engineers, and support or operations people who already work with Kubernetes and want to ask questions about a cluster in plain language.