MCP server · Developer tools
Kubernetes MCP server (mcp-k8s)
by silenceper
Ask your AI to look at and change your Kubernetes cluster in plain words, instead of typing kubectl commands.
This is a small helper program 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 is usually managed with long, hard-to-remember commands. If you or your team run things on Kubernetes, this lets you just describe what you want in normal language.
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 system. This one connects your AI to your Kubernetes cluster, so the AI can look up what is running there and, if you allow it, create, change or remove things. You ask in plain words, and the helper does the technical work in the background.
What this MCP server does
You ask your AI something about your cluster, like which apps are running or why one is broken. The AI sends that request to this helper program. The helper talks to your Kubernetes cluster using your kubeconfig file, which is the login file that lets tools reach the cluster. The cluster answers, and the helper passes the answer back to your AI, which explains it to you in normal words. If write actions are switched on, the AI can also make changes for you, like creating or deleting a resource.
Click to zoomWhat you can do with it
- List the kinds of resources your cluster supports, including custom ones
- Look up the details of one specific resource
- List all items of a resource type, with filters
- Create new resources (only if you switch this on)
- Update existing resources (only if you switch this on)
- Delete resources (only if you switch this on)
- List and inspect Helm releases, and install, upgrade or remove them if enabled
Try asking your AI
- “What pods are running in the default namespace right now?”
- “Show me the details of the deployment called web-app.”
- “List all Helm releases in the cluster.”
- “Why might the pod api-7f8d be failing? Look at its details.”
What it gives back to you
You get answers in the chat, in normal words. That can be a list of resources, the details of one resource, or a summary of what is running. If you asked for a change and write actions are enabled, the AI tells you what it changed. You do not get raw command output unless the AI chooses to show it.
Before you start
What you need
- A Kubernetes cluster you can reach
- A kubeconfig file, which is the login file that lets tools connect to your cluster
- The mcp-k8s program itself, downloaded from its releases page or run with Docker
- An MCP-compatible AI app, like Cursor or the Claude desktop app
Good to know
If you turn on the write options, your AI can create, change or delete real things in your cluster, so keep those switches off unless you really need them and trust what you are asking.
Install it with your AI
Add Kubernetes MCP server (mcp-k8s) 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 (mcp-k8s), 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.
Who it's for
Developers, DevOps and operations people who manage Kubernetes clusters and want to do everyday tasks by describing them instead of typing kubectl commands.
