Server Scraper

About

Server Scraper offers a free, open-source solution for extracting structured, clean content from web pages. It leverages Mozilla Readability to convert articles, blogs, and documentation into readily consumable markdown text, while also gathering essential data like links and metadata (titles, OG tags, canonical URLs). Designed for effortless integration with AI clients such as Claude Desktop, Cursor, and VS Code Copilot via the Model Context Protocol (MCP), it operates with zero authentication or configuration, providing a powerful, no-cost alternative for developers and AI users seeking to enrich their model context with reliable web data.

Key Features

• Extract clean text content from a URL using Readability-powered engine
• 0 GitHub stars
• Extract comprehensive metadata including title, description, OG tags, canonical URL, and favicon
• Search for specific query strings within a page and return matching lines
• Batch scrape multiple URLs, retrieving titles and excerpts for each
• Get all links with href and anchor text from a page

Use Cases

• Summarize API documentation or articles from a URL using an AI assistant
• Extract all links and detailed metadata from a webpage for analysis
• Perform targeted searches or batch scrapes on multiple URLs for quick overviews