Web Scraping

Self-hosted, Tavily-compatible web search, extract, crawl and map tools for AI agents.

LionScraper Python: MCP stdio + CLI + HTTP API bridging AI to LionScraper browser extension.

Web-scraping toolkit with 22 tools for structured web data as JSON for AI agents.

Open-source web scraper for AI agents with scrape, crawl, and map tools

Token compression for web content — 70-80% reduction from HTML to clean markdown

40 Apify public-data tools for leads, news, SEO, jobs, SEC, procurement, and registries.

Your agent seeks what search can't find. A self-hosted perception MCP server.

Web scraping & search for AI agents: extract, SearXNG search, rerank, robots compliance. No API key.

Multi-provider proxy infrastructure for AI/ML. Geo, sessions, cost-aware routing, usage tools.

Read MyFigureCollection.net: search figures, JAN barcode lookup, shop prices, collections and clubs.

Stealth browser MCP server — anti-detection Chromium with snapshot-first agent interface

Scrape messages, extract leads from public Telegram channels. No login required.

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

Crawl and analyse websites for SEO errors using Crawlee with SQLite storage

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

License-first federated image search with attribution, dimensions, and download tooling.

Cloaked headless browser for AI agents — stealth TLS, smart extraction, SPA fallback

MCP server for web content fetching, summarizing, comparing, and extracting information

Stealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.

Self-healing web access for AI agents — recovers through bot blocks, captchas and JS pages.