Skip to main content
just-scrape can be installed as a skill for AI coding agents via Vercel’s skills.sh. This lets agents like Claude, Cursor, and others call ScrapeGraphAI commands directly during a coding session.

​
Install the skill

bunx skills add https://github.com/ScrapeGraphAI/just-scrape
Browse the skill: skills.sh/scrapegraphai/just-scrape/just-scrape

​
What this enables

Once installed, your coding agent can:
  • Scrape a website to gather data needed for a task
  • Convert documentation pages to markdown for context
  • Search the web and extract structured results
  • Check your credit balance mid-session
  • Browse request history

​
How agents use it

Agents call just-scrape in --json mode for clean, token-efficient output: 
just-scrape smart-scraper https://api.example.com/docs \
  -p "Extract all endpoint names, methods, and descriptions" \
  --json

just-scrape search-scraper "latest release notes for react-query" \
  --num-results 3 --json

​
Tips

  • Set SGAI_API_KEY in your shell profile so the skill picks it up automatically.
  • Always use --json — agents don’t need spinners or banners.
  • Pass --schema with a JSON schema to get typed, predictable output:
just-scrape smart-scraper https://example.com \
  -p "Extract company info" \
  --schema '{"type":"object","properties":{"name":{"type":"string"},"founded":{"type":"number"}}}' \
  --json

​
MCP Server alternative

For a deeper integration in Cursor or Claude Desktop, use the MCP Server instead, which exposes ScrapeGraphAI as native tools available to the AI model.