MCP SERVER · OFFICIAL PROJECTScrapeGraph AI's official server — extract structured data from a page or a search, run async multi-page crawls, and set monitors that watch a site for changes.
LABSCO SUMMARY
The schema tool paired with extract is the workflow that sets this apart from a plain fetcher: describe the fields you want, get a JSON Schema, and pull data that already matches it. The monitor tools push it further — instead of re-scraping on your own cron, monitor_create schedules the check and monitor_activity tells you which runs actually saw the page change.
ScrapeGraphAI's official server against their API v2: 17 tools for AI-powered extraction, search, crawling and scheduled monitoring, plus schema generation and account reads. Runs locally over stdio, or as a hosted endpoint your client connects to.
A ScrapeGraph AI API key, held in SGAI_API_KEY (or passed through the MCP config). Python 3.13 or higher if you run it locally from a clone; the hosted endpoint needs no local installation. It targets API v2 at https://v2-api.scrapegraphai.com/api by default; SGAI_API_URL overrides the base URL and SGAI_TIMEOUT sets the request timeout, which defaults to 120 seconds.
One command plus a key — npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude, then supply credentials
USE CASES
Generate the schema for what you want, then extract straight into that shape, so the result is structured data rather than HTML you have to pick apart.
Run an AI search that returns structured results, and follow up by extracting from the specific pages worth a closer look.
Start an async crawl, poll it until it finishes, and pause or resume the job if you need to — without holding a connection open the whole time.
Schedule a monitor against a prompt, then poll its activity to see which runs detected a change and what the diffs were, rather than re-scraping on your own timer.
Check remaining credits before a big crawl and review recent requests to see where the budget went.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
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_resumeResume a stopped crawl job (API v2 POST /crawl/:id/resume).
crawl_startStart an asynchronous multi-page crawl (API v2 POST /crawl).
Poll crawl_get_status with the returned id.
crawl_stopStop a running crawl job (API v2 POST /crawl/:id/stop).
creditsReturn remaining API credits (API v2 GET /credits).
extractExtract structured data from a webpage using AI (API v2 POST /extract).
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_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.
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.
monitor_deleteDelete a monitor (API v2 DELETE /monitor/:id).
monitor_getGet one monitor by id (API v2 GET /monitor/:id).
monitor_listList monitors (API v2 GET /monitor).
monitor_pausePause a monitor (API v2 POST /monitor/:id/pause).
monitor_resumeResume a paused monitor (API v2 POST /monitor/:id/resume).
schemaGenerate or augment a JSON Schema from a natural-language prompt (API v2 POST /schema).
scrapeFetch page content (API v2 POST /scrape).
searchAI-powered web search with structured data extraction (API v2 POST /search).
BEFORE YOU INSTALL
17 tools when we connected. Version 3 renamed tools without aliases, such as smartscraper to extract and searchscraper to search, and removed markdownify, sitemap and agentic_scrapper. For markdown, use scrape with output_format="markdown".
CONTEXT COST
Rated by the size of the 17 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claudehttps://sgai-mcp-main.onrender.com/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
{
"mcpServers": {
"@ScrapeGraphAI-scrapegraph-mcp": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@ScrapeGraphAI/scrapegraph-mcp",
"--config",
"{\"scrapegraphApiKey\":\"<YOUR_SGAI_API_KEY>\"}"
]
}
}
}<YOUR_SGAI_API_KEY> is your key from the ScrapeGraph Dashboard (https://dashboard.scrapegraphai.com).
{
"mcpServers": {
"scrapegraph-mcp": {
"command": "npx",
"args": [
"mcp-remote@0.1.25",
"https://sgai-mcp-main.onrender.com/mcp",
"--header",
"X-API-Key:<YOUR_API_KEY>"
]
}
}
}<YOUR_API_KEY> is your key from the ScrapeGraph Dashboard (https://dashboard.scrapegraphai.com).
{
"mcpServers": {
"scrapegraph-mcp": {
"url": "https://sgai-mcp-main.onrender.com/mcp",
"headers": {
"X-API-Key": "<YOUR_API_KEY>"
}
}
}
}<YOUR_API_KEY> is your key from the ScrapeGraph Dashboard (https://dashboard.scrapegraphai.com).
git clone https://github.com/ScrapeGraphAI/scrapegraph-mcp
cd scrapegraph-mcp
pip install -e .Add this to claude_desktop_config.json (needs Python 3.13 or higher on PATH as python):
{
"mcpServers": {
"scrapegraph-mcp-local": {
"command": "python",
"args": [
"-m",
"scrapegraph_mcp.server"
],
"env": {
"SGAI_API_KEY": "<YOUR_SGAI_API_KEY>"
}
}
}
}MCP servers
Xquik-dev
O-mega-Enterprise
apify
mysleekdesigns