WebClone
Website cloning engine with intelligent crawling, asset downloading, PDF generation, authentication support, and dynamic content r
WebClone is a Python-based website cloning engine created by Ruslan Magana that provides complete website archival capabilities through CLI, GUI, and MCP server interfaces. The implementation features asynchronous concurrent downloads with configurable depth and concurrency limits, comprehensive asset preservation (CSS, JavaScript, images, fonts), PDF generation via Chrome DevTools Protocol, cookie-based authentication with session persistence, and Selenium integration for JavaScript-heavy single-page applications. The MCP server exposes tools for cloning entire websites, downloading specific files, managing authentication sessions, listing saved cookies, and retrieving site metadata. It's designed for website archival, competitive research, training dataset creation, documentation backup, and AI-assisted web scraping workflows that require authenticated access to protected content.
Source
Repository: https://github.com/ruslanmv/webclone
Maintain WebClone?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[WebClone on getagentictools](https://getagentictools.com/mcp/ruslanmv-webclone?ref=badge)