mcp-kubernetes-server
by feiskyer
A Model Context Protocol (MCP) server to enable Claude, Cursor and other AI tools to interact with Kubernetes cluster via kubectl. It allows AI tools to access and manage your Kubernetes resources.
Last updated: N/A
What is mcp-kubernetes-server?
mcp-kubernetes-server is a Model Context Protocol (MCP) server that acts as a bridge between AI tools (like Claude, Cursor, ChatGPT Copilot, and Github Copilot) and your Kubernetes cluster. It allows these AI tools to interact with your Kubernetes cluster using kubectl commands.
How to use mcp-kubernetes-server?
The server can be installed using Docker or NPX. You need to configure the MCP servers in your AI client (e.g., Claude Desktop, Cursor) with the appropriate command and arguments, including the path to your kubeconfig file. The provided examples show how to configure the server using either Docker or NPX with uv.
Key features of mcp-kubernetes-server
Enables AI tools to interact with Kubernetes clusters
Uses kubectl to manage Kubernetes resources
Supports multiple AI clients (Claude, Cursor, ChatGPT Copilot, Github Copilot)
Installation via Docker or NPX
Configurable kubeconfig path
Use cases of mcp-kubernetes-server
Using AI to analyze Kubernetes cluster state
Automating Kubernetes deployments with AI assistance
Troubleshooting Kubernetes issues with AI insights
Generating Kubernetes manifests using AI
Managing Kubernetes resources through AI-powered interfaces
FAQ from mcp-kubernetes-server
What is MCP?
What is MCP?
MCP stands for Model Context Protocol, a protocol that allows AI tools to interact with external systems.
What AI tools are supported?
What AI tools are supported?
Claude, Cursor, ChatGPT Copilot, and Github Copilot are explicitly mentioned, but any AI tool that supports MCP should be compatible.
How do I find my kubeconfig path?
How do I find my kubeconfig path?
The default location is usually ~/.kube/config, but it may be different depending on your setup.
What if I encounter issues during installation?
What if I encounter issues during installation?
Ensure that kubectl is correctly installed and configured, and that your kubeconfig file is valid. Check the logs for any error messages.
Where can I report bugs or contribute?
Where can I report bugs or contribute?
The project is open source on GitHub at feiskyer/mcp-kubernetes-server. You can report issues or submit pull requests there.