Web Scrapper Service

Example Use Cases

• 1

  Extract clean, readable content from web pages for AI processing or automation.

• 2

  A headless, robust web scraping tool integrated via MCP stdio/JSON-RPC.

• 3

  Convert web content into Markdown, text, or HTML formats for seamless integration with IDEs and AI tools.

Description

This MCP server uses a headless browser with Playwright, BeautifulSoup, and Markdownify to scrape web pages robustly, handling errors like timeouts and Cloudflare challenges. It outputs content in Markdown, text, or HTML formats, making it easy to integrate with AI tools and IDEs via the Model Context Protocol. The service is dockerized, configurable via environment variables, and supports per-domain rate limiting for responsible scraping.