← Back to Robot Resources Scraper

Install Robot Resources Scraper

Pick your client, copy the command, done.

1

Add it to Claude Code

claude mcp add robot-resources-scraper -- npx -y @robot-resources/scraper-mcp

Available Tools (2)

Once configured, Robot Resources Scraper gives your AI agent access to:

scraper_compress_urlCompress a single web page into markdown with 70-90% fewer tokens.
urlmodetimeoutmaxRetries
scraper_crawl_urlCrawl multiple pages from a starting URL using BFS link discovery.
urlmaxPagesmaxDepthmodeincludeexcludetimeout

Try It Out

After setup, try these prompts with your AI agent:

Compress https://docs.example.com/getting-started into markdown for me.
Crawl the documentation at https://docs.example.com with a maximum of 20 pages.
Scrape the article at https://blog.example.com using the stealth mode to avoid bot detection.
Crawl https://example.com/docs up to a depth of 3 pages.
Prerequisites & system requirements
  • An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
  • Node.js 18+ with npm/npx installed
Alternative installation methods

Global NPM

npm install -g @robot-resources/scraper-mcp

Keep this setup from going cold

Save the docs, env vars, and workflow around Robot Resources Scraper in Conare so Claude Code, Codex, and Cursor remember it next time.

Remember this setup