A straightforward wrapper around wget that lets Claude download entire websites for local browsing or archival. Exposes a single download_website tool that recursively crawls sites, preserves directory structure, converts links to work offline, and restricts downloads to the target domain. You can control crawl depth and output location. Handy when you need to grab documentation sites, create offline copies of web resources, or analyze site structure. Requires wget installed locally, works across macOS, Linux, and Windows. The tool handles all the wget flags for you, so you get proper recursive downloading with converted links without wrestling with command line options.
This MCP server provides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.
The server requires wget to be installed on your system.
Using Homebrew:
brew install wget
sudo apt-get update
sudo apt-get install wget
sudo dnf install wget
choco install wget
The server provides a tool called download_website with the following parameters:
url (required): The URL of the website to downloadoutputPath (optional): The directory where the website should be downloaded. Defaults to the current directory.depth (optional): Maximum depth level for recursive downloading. Defaults to infinite. Set to 0 for just the specified page, 1 for direct links, etc.{
"url": "https://example.com",
"outputPath": "/path/to/output",
"depth": 2 // Optional: Download up to 2 levels deep
}
The website downloader:
npm install
npm run build
{
"mcpServers": {
"website-downloader": {
"command": "node",
"args": ["/path/to/website-downloader/build/index.js"]
}
}
}