What prerequisites are needed to run mcp-kubernetes-server?
A working Kubernetes cluster, a valid kubeconfig file, kubectl and helm installed in the system PATH, and Python ≥3.11 if using uvx (not required for Docker).
@feiskyer
基本情報
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning t
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"kubernetes": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--mount",
"type=bind,src=/home/username/.kube/config,dst=/home/mcp/.kube/config",
"ghcr.io/feiskyer/mcp-kubernetes-server"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
mcp-kubernetes-server is a Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It translates natural language requests from AI assistants into kubectl commands or direct Kubernetes API calls, executing them against the target cluster and returning structured responses.
Install via Docker or uvx. Configure in the mcpServers section of your AI client (Claude Desktop, Cursor, ChatGPT Copilot, GitHub Copilot). Provide a valid kubeconfig either via the KUBECONFIG environment variable (uvx) or by mounting the file into the container (Docker). Ensure kubectl, helm, and Python ≥3.11 (for uvx) are installed. Run with optional command-line flags to disable specific operations or change transport (stdio, sse, streamable-http).
k8s_auth_can_i, k8s_auth_whoami).A working Kubernetes cluster, a valid kubeconfig file, kubectl and helm installed in the system PATH, and Python ≥3.11 if using uvx (not required for Docker).
Set the `KUBECONFIG` environment variable to the path of your kubeconfig file, or when using Docker mount the kubeconfig file to `/home/mcp/.kube/config`.
Yes, use the `--disable-write` flag to block all write operations or `--disable-delete` to block deletions. Similarly, `--disable-kubectl` and `--disable-helm` disable those command executers.
mcp-kubernetes-server supports three transports: `stdio` (default for uvx), `sse`, and `streamable-http`. Use the `--transport` flag to choose, and specify `--host`/`--port` for the server transports.
The server works with any AI client that supports the Model Context Protocol, including Claude Desktop, Cursor, ChatGPT Copilot, and GitHub Copilot.
A docker MCP Server (modelcontextprotocol)

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a
MCP server connecting to Kubernetes
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Find, price and rent GPUs on Lium from Claude, ChatGPT, Codex or any MCP client. Search live GPU availability and prices (H100, H200, B200, RTX 4090 and more), estimate provider earnings, and with Sign in with Lium or a
コメント