About Kubernetes Mcp Server
Kubernetes Mcp Server is an MCP server for managing a Kubernetes cluster. It requires a running cluster selected as the current context in `~/.kube/config`.
Key features
- 01Manage a Kubernetes cluster
- 02Use the current kubeconfig context
- 03Inspect with MCP inspector
Use cases
- 01Interact with the configured cluster
- 02Run the server locally
- 03Debug the server with MCP inspector
MCP support
It exposes tools for interacting with a Kubernetes cluster to MCP clients. The server uses the current context configured in `~/.kube/config`.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEKubernetes MCP server
MCP server for managing a Kubernetes cluster
Prerequisities
A running Kubernetes cluster set as the current context in ~/.kube/config. The current context can be inspected using kubectl config current-context.
The quickest way to get a running cluster is to use minikube. Run minikube start once installed.
Without a running cluster set as the current context, the MCP server will not be functional.
Note that while none of the tools contain destructive behavior, it's best to be cautious when exposing access to your cluster.
Running the server
Locally: npm run dev
Using Claude Desktop: Add the following to the mcpServers key of your claude_desktop_config.json file:
"kubernetes": {
"command": "node",
"args": ["/Users/bry24/Documents/Projects/basic-mcp/dist/index.js"]
}
Note that the alias of the server can be anything. The following guide is a useful example of how to configure MCP in the Claude Desktop App.
Once the MCP server is configured correctly, you should be able to use the tools to interact with your cluster. Example:

Debugging the server
Using MCP inspector: npm run inspect
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.