MCP Servers / web-scraping / ScrapeGraph AI

ScrapeGraph AI

JSON →

stdionone★ 77web-scraping

AI-powered web scraping using the ScrapeGraph AI API. Requires an API key.

github ↗

Install

How to run this server

[ { "cmd": "npx -y @smithery/cli", "imports": [] } ]

server path: scrapegraph-ai

Tools

What this server exposes

scrape

POST /scrape with output_format options: markdown, html, screenshot, branding, links, images, summary

extract

POST /extract requiring website_url and user_prompt; optional output_schema

POST /search with num_results 1–20; supports country_search, time_range, output_schema

crawl_start

POST /crawl with extraction_mode: markdown, html, links, images, summary, branding, screenshot

crawl_get_status

GET /crawl/:id to poll until status is completed

crawl_stop

POST /crawl/:id/stop

crawl_resume

POST /crawl/:id/resume

schema

POST /schema to generate or augment a JSON Schema from a prompt

credits

GET /credits

history

GET /history with pagination and service filter

monitor_create

POST /monitor to create a monitor

monitor_list

GET /monitor to list monitors

monitor_get

GET /monitor/:id to get a specific monitor

monitor_pause

POST /monitor/:id/pause

monitor_resume

POST /monitor/:id/resume

monitor_delete

DELETE /monitor/:id

monitor_activity

GET /monitor/:id/activity for paginated tick history with id, createdAt, status, changed, elapsedMs, diffs

Configuration

Environment & auth

authnone

envSGAI_API_URL

envSGAI_API_KEY

envSCRAPEGRAPH_API_BASE_URL

envYOUR_API_KEY

envBASE_URL

Resources

githubhttps://github.com/ScrapeGraphAI/scrapegraph-mcp ↗