MCPs › Data & APIs › crw
Web search and web scraping for AI agents in one fast, single-binary MCP server. crw searches the web, scrapes any URL to clean markdown or HTML, maps a site's links, runs bounded recursive crawls, and extracts structured JSON from pages. Built-in anti-bot handling, JavaScript rendering, and proxy rotation recover content that a plain fetch and lighter scrapers miss. Open source (AGPL), local-first, and zero-config via npx, or use this managed cloud endpoint. A leaner, self-hostable alternative to Firecrawl and Tavily for agent web access, docs research, and structured data extraction.
Not monetized yet
Turn crw’s tool calls into revenue: one disclosed sponsored slot, 70% revenue share, fail-open by design.
Install crw
For anyone using crw — no Lulu account neededclaude mcp add --transport http crw https://crw--fastcrw.run.tools
Real-time weather for any city, built on the lulu-ads widget gallery. First-party, free forever.
View server →FAQ
Run: claude mcp add --transport http crw https://crw--fastcrw.run.tools
Yes — it’s a remote MCP server, so no local install is needed.
ChatGPT: Settings → Connectors → Advanced → Developer mode → Add connector, then paste https://crw--fastcrw.run.tools.
Claude.ai: Settings → Connectors → Add custom connector, then paste the same URL.
Unrated out of 100, computed from cross-registry traction signals (installs, stars, registry presence) — never influenced by sponsorship.
Similar servers
Works well together