MCP.so
ログイン

Site Cloner MCP Server

@SarthakMishra

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

SarthakMishra

Site Cloner MCP Server について

MCP server to help LLMs clone websites by providing tools to fetch, analyze, and download website assets.

#site-cloner#website-cloning#llm-tools

Site Cloner 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": {
    "site-cloner": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "site-cloner-mcp",
        "."
      ]
    }
  }
}

Site Cloner 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 Site Cloner MCP Server?

Site Cloner MCP Server is an MCP (Model Context Protocol) server that helps LLMs like Claude clone websites by providing tools to fetch, analyze, and download website assets. It is built for developers and AI users who need to capture local copies of web pages.

How to use Site Cloner MCP Server?

The server runs in Docker. Build the image (docker build -t site-cloner-mcp .) and run the container (docker run -i --rm site-cloner-mcp). For persistent storage, mount a volume. To integrate with Cursor, add a project-level .cursor/mcp.json or a global MCP server pointing to the Docker command. Once configured, ask Claude to clone a website, and it will use the available tools to fetch, parse, download, and organize assets.

Key features of Site Cloner MCP Server

  • Fetch HTML content from any URL
  • Extract assets (CSS, JavaScript, images, fonts, etc.) from HTML
  • Download individual assets to a local directory
  • Parse CSS files to extract linked assets (fonts, images)
  • Create a sitemap of a website
  • Analyze page structure and layout

Use cases of Site Cloner MCP Server

  • Clone a website for offline review or archival
  • Download all assets of a page for local development
  • Generate a sitemap for small websites
  • Analyze the structure of a webpage programmatically
  • Extract and save CSS-linked resources like fonts and images

よくある質問

1

Why is the server not showing up in Cursor?

Restart Cursor, check your configuration file syntax, and ensure Docker is installed and running. Look at Cursor’s MCP logs (`Output` → `Cursor MCP`) for errors. Try running the server manually with `docker run -i --rm site-cloner-mcp`.

2

How do I fix a “ModuleNotFoundError: No module named 'site_cloner'”?

Check that the package name in `pyproject.toml` is correct and that import statements do not include the `src.` prefix. Rebuild the Docker image with `docker build --no-cache -t site-cloner-mcp .`.

3

Where do downloaded files go?

The server automatically organizes downloaded assets into subdirectories based on content type: `html`, `css`, `js`, `images`, `fonts`, `videos`, `other`. Use a mounted volume to persist them outside the container.

4

Are there any legal considerations when using this server?

Be mindful of copyright and terms of service restrictions when cloning sites. Some websites may block automated requests; you might need to adjust the user agent string.

5

Does the server have any dependencies beyond Docker?

Yes, Docker must be installed on your system. The server itself is packaged as a Docker image and requires no additional local runtime.

コメント

「その他」の他のコンテンツ