MCP.so
ログイン

Click MCP Server

@crowecawcaw

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

crowecawcaw

Click MCP Server について

Turn click CLIs into MCP servers with one line of code

Click MCP 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": {
    "click-mcp": {
      "command": "python",
      "args": [
        "my_app.py",
        "mcp"
      ]
    }
  }
}

Click MCP 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。

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。

概要

What is click-mcp?

click-mcp is a Python library that extends Click applications with Model Context Protocol (MCP) support, allowing AI agents to discover and interact with CLI tools programmatically. It provides a simple decorator that converts Click commands into MCP tools.

How to use click-mcp?

Install via pip (pip install click-mcp), then decorate your Click group with @click_mcp(). Run the MCP server using python my_app.py mcp (or a custom command name if configured). The decorator automatically converts Click commands into MCP tools with named parameters and dot‑notation for nested groups.

Key features of click-mcp

  • Simple @click_mcp decorator syntax
  • Automatic conversion of Click commands to MCP tools
  • Support for nested command groups
  • Support for positional arguments
  • Stdio‑based MCP server for easy integration

Use cases of click-mcp

  • Turn any existing Click CLI into an MCP‑compatible tool
  • Allow AI agents to invoke CLI commands with structured parameters
  • Expose complex nested command hierarchies as discoverable MCP tools

よくある質問

1

What is the Model Context Protocol (MCP)?

MCP is an open standard for AI agents to interact with tools and applications in a structured way.

2

What are the dependencies or runtime requirements?

click-mcp requires Python and the Click library. The README assumes a standard Python environment.

3

How can I customize the MCP command name?

Use the `command_name` parameter in the `@click_mcp` decorator, e.g. `@click_mcp(command_name="start-mcp")`.

4

How are command errors handled?

When a Click command raises an exception, click-mcp captures the error and returns it as part of the MCP response, enabling AI agents to handle errors gracefully.

5

How are nested commands named when exposed as MCP tools?

Nested commands use dot notation (e.g., `users.create`).

コメント

「その他」の他のコンテンツ