Search Scrape (SearXNG)

Combines SearXNG federated search with Rust-native content extraction to provide privacy-focused web search and intelligent scraping across multiple search engines with readability algorithms and specialized documentation parsing.

Pure Rust web search and scraping MCP server that combines SearXNG federated search with advanced content extraction capabilities. The implementation uses a containerized SearXNG instance for privacy-focused search across multiple engines (Google, DuckDuckGo, Bing, Startpage) while providing a sophisticated Rust-native scraper that leverages readability algorithms, language detection, and content preprocessing to extract clean text from web pages. Features comprehensive caching with Moka, concurrent request limiting, retry logic with exponential backoff, and specialized extraction for documentation sites like mdBook, making it valuable for AI applications that need reliable web research capabilities without depending on external scraping services or compromising user privacy through direct search engine APIs.