MCP.so
ログイン

MCP Kubernetes Server

@MCP-Mirror

基本情報

カテゴリ

クラウドとインフラ

トランスポート

stdio

作者

MCP-Mirror

MCP Kubernetes Server について

Mirror of

MCP Kubernetes Server の設定

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": {
    "abhijeetka_mcp-k8s-server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@abhijeetka/mcp-k8s-server",
        "--client",
        "claude"
      ]
    }
  }
}

MCP Kubernetes Server のツール

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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is MCP Kubernetes Server?

MCP Kubernetes Server is an MCP (Model Context Protocol) server that provides control over Kubernetes clusters through interactions with LLMs. It wraps kubectl commands to offer a simple interface for managing Kubernetes resources, enabling seamless interaction between language models and Kubernetes operations.

How to use MCP Kubernetes Server?

Install via Smithery or configure the MCP server in your Claude Desktop config (e.g., using uv to run kubernetes.py). The server exposes tools that LLMs can call using natural language prompts such as "Create a new nginx deployment with 3 replicas."

Key features of MCP Kubernetes Server

  • Wraps kubectl commands for common Kubernetes operations.
  • Supports create, scale, update, delete, and inspect resources.
  • Includes port-forward, expose, label, and annotation management.
  • Provides context switching and namespace-aware operations.
  • Designed for natural language interaction through LLMs.

Use cases of MCP Kubernetes Server

  • Manage deployments, pods, services, and other resources via conversational prompts.
  • Automate cluster operations without memorizing kubectl syntax.
  • Enable LLMs to maintain context across multi-step Kubernetes tasks.
  • Validate and execute resource changes with reduced command complexity.

よくある質問

1

What do I need to run the server?

You need Python 3.x, the MCP framework, and Kubernetes cluster access configured via `kubectl`.

2

How does the server interact with LLMs?

Each tool function is decorated with `@mcp.tool()`, making them accessible to LLMs through the Model Context Protocol.

3

Can I use it with Claude Desktop?

Yes. Add a JSON entry to your Claude Desktop config with the appropriate command (e.g., `uv run kubernetes.py`).

4

What if I want to install it automatically?

Run `npx -y @smithery/cli install @abhijeetka/mcp-k8s-server --client claude` via Smithery.

5

Are there any security considerations?

Yes. Ensure proper access controls on your cluster, run the MCP server in a secure environment, and authenticate/authorize API access.

コメント

「クラウドとインフラ」の他のコンテンツ