crawl_start

MCP tool from Scrapegraph MCP by ScrapeGraphAI

POST /crawl — extractionmode markdown / html / links / images / summary / branding / screenshot

How to use it

crawl_start is exposed by the Scrapegraph MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the crawl_start tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Scrapegraph MCP

$npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude

FULL SCRAPEGRAPH MCP LISTING

Other tools in Scrapegraph MCP (9)

crawl_get_status

GET /crawl/:id (poll until status: completed)

credits

GET /credits

extract

POST /extract (requires websiteurl + userprompt; optional outputschema)

history

GET /history (paginated, service filter)

monitor_activity

GET /monitor/:id/activity (paginated tick history: id, createdAt, status, changed, elapsedMs, diffs)

mypy

Static type checker

schema

POST /schema (generate or augment a JSON Schema from a prompt)

scrape

POST /scrape (outputformat: markdown, html, screenshot, branding, links, images, summary)

POST /search (numresults 1–20; supports countrysearch, timerange, outputschema)