scrapegraphai

The ScrapeGraphAI MCP Server is a production-ready Model Context Protocol (MCP) server that connects Large Language Models (LLMs) to the ScrapeGraph AI API.

Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Extract: Extract structured data from a webpage using AI (API v2 POST /extract).
  • Search: AI-powered web search with structured data extraction (API v2 POST /search).
  • Crawl Start: Start an asynchronous multi-page crawl (API v2 POST /crawl). Poll crawl_get_status with the returned id.

What data it sees

Do you need an account

An API key from the service settings is required

The ScrapeGraphAI MCP Server is a production-ready Model Context Protocol (MCP) server that connects Large Language Models (LLMs) to the ScrapeGraph AI API. It enables AI assistants like Claude and Cursor to perform AI-powered web scraping, research, and crawling directly through natural language interactions.

Server tool list (17)

Raw names from tools/list. Only developers need these.

extractExtract structured data from a webpage using AI (API v2 POST /extract).
searchAI-powered web search with structured data extraction (API v2 POST /search).
crawl_startStart an asynchronous multi-page crawl (API v2 POST /crawl). Poll crawl_get_status with the returned id.
crawl_get_statusRetrieve the results of an asynchronous SmartCrawler operation. This tool fetches the results from a previously initiated crawling operation using the request_id. The crawl request processes asynchronously in the background. Keep polling this endpoint until the status field indicates 'completed'. While processing, you'll receive status updates. Read-only operation that safely retrieves results without side effects.
crawl_stopStop a running crawl job (API v2 POST /crawl/:id/stop).
crawl_resumeResume a stopped crawl job (API v2 POST /crawl/:id/resume).
creditsReturn remaining API credits (API v2 GET /credits).
historyList recent API requests (API v2 GET /history). v2 accepts page/limit/service. The legacy endpoint/offset params are kept as aliases and translated client-side (endpoint -> service, offset -> page when it divides limit). status filtering was removed in v2.
monitor_createCreate a scheduled monitor job (API v2 POST /monitor). The v2 API expects a `formats` array. This tool wraps `prompt` (+ optional `output_schema`) into a `{type: "json", ...}` format entry for you.
schemaGenerate or augment a JSON Schema from a natural-language prompt (API v2 POST /schema).
monitor_listList monitors (API v2 GET /monitor).
monitor_getGet one monitor by id (API v2 GET /monitor/:id).
monitor_pausePause a monitor (API v2 POST /monitor/:id/pause).
monitor_resumeResume a paused monitor (API v2 POST /monitor/:id/resume).
monitor_deleteDelete a monitor (API v2 DELETE /monitor/:id).
monitor_activityPoll per-run tick history for a monitor (API v2 GET /monitor/:id/activity). Returns the ticks produced on each scheduled run (`id`, `createdAt`, `status`, `changed`, `elapsedMs`, `diffs`) plus `nextCursor` when more results are available. Mirrors `sgai.monitor.activity()` in scrapegraph-py v2.
scrapeFetch page content (API v2 POST /scrape).
scrapegraphai: connect to Claude, ChatGPT, Cursor · Connectors.fun