Тег «mcpserver #crawling #agents #realtime #mcpservers» — 2

serpdive

smithery.ai

**Real-time web search built for AI agents.** One tool, `serpdive_search`, returns the actual content of the best pages — extracted, cleaned, and sized for LLMs — not a list of links to crawl. ## Why SERPdive On a [public, replayable 1,000-question benchmark](https://github.com/edendalexis/serpdive-benchmark) against Tavily: - **Same speed** (median ~1.7 s server-side) - **20.2% fewer tokens** fed to your LLM per search - 🏆 **60.7% of decided quality duels** won Same ques

Tavily Web Search and Extraction Server

smithery.ai

Enable AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites systematically. Enhance your AI's capabilities with powerful tools for intelligent data retrieval and analysis from the web. Seamlessly integrate advanced search and extraction features into your MCP client workflows.