Scrapegraph Ai for AI agents

ScrapeGraphAI extracts structured data from websites using natural language prompts instead of hand-written scraping rules, aimed at developers automating data pipelines. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Scrapegraph Ai See the 27 actions ↓

Web data and scrapingAPI keyMCP + RESTscrapegraphai.com

AUDIT LOG · SCRAPEGRAPH AIPOLICY: acme-support

09:41:07 · claude · u_8f2read

scrapegraph_ai.list_scheduled_jobs

List Scheduled Jobs✓ allowed · 212ms

09:41:08 · claude · u_8f2read

scrapegraph_ai.get_credits

Get Credits✓ allowed · 164ms

09:41:09 · claude · u_8f2write

scrapegraph_ai.toonify

Convert JSON to TOON Format✓ approved · approved by user

EVERY SCRAPEGRAPH AI CALL, ON THE RECORD

01 · USE CASES

What agents do in Scrapegraph Ai.

Convert a webpage to markdown

Turns a target page into clean markdown text for an agent to read or summarize.

Check scrape history before rerunning

Looks up a previous scrape job's results before deciding whether it needs to run again.

Review credits before a large crawl

Reads remaining credits so a multi-page crawl is not started without enough balance to finish.

02 · ACTIONS

27 Scrapegraph Ai actions, graded by risk.

Every Scrapegraph Ai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

scrapegraph_ai.get_credits
Get Credits
scrapegraph_ai.search_scraper
Search Scraper
scrapegraph_ai.get_webhook_logs
Get Webhook Logs
scrapegraph_ai.get_scrape_history
Get Scrape History
scrapegraph_ai.get_usage_timeline
Get Usage Timeline
scrapegraph_ai.get_crawler_history
Get Crawler History
scrapegraph_ai.get_sitemap_history
Get Sitemap History
scrapegraph_ai.list_scheduled_jobs
List Scheduled Jobs
scrapegraph_ai.get_live_session_url
Get Live Session URL
scrapegraph_ai.search_scraper_status
Check SearchScraper Status
scrapegraph_ai.get_markdownify_history
Get Markdownify History
scrapegraph_ai.get_endpoint_suggestions
Get Endpoint Suggestions
scrapegraph_ai.get_smartscraper_history
Get Smartscraper History
scrapegraph_ai.get_searchscraper_history
Get Searchscraper History
scrapegraph_ai.get_agentic_scraper_history
Get Agentic Scraper History
scrapegraph_ai.validate_api_key
Validate API Key

+ 1 MORE

write

Create and change things. Allow, or ask the user first.

scrapegraph_ai.toonify
Convert JSON to TOON Format
scrapegraph_ai.save_endpoint
Save Endpoint Configuration
scrapegraph_ai.generate_schema
Generate Schema
scrapegraph_ai.submit_feedback
Submit Feedback
scrapegraph_ai.markdownify_status
Markdownify Status
scrapegraph_ai.smart_scraper_start
Start Smart Scraper
scrapegraph_ai.start_smart_crawler
Start Smart Crawler (Async)
scrapegraph_ai.smart_crawler_status
SmartCrawler Status
scrapegraph_ai.smart_scraper_status
Look Up SmartScraper Request
scrapegraph_ai.submit_product_feedback
Submit Product Feedback

destructive

Delete, cancel or archive. Ask first, or deny outright.

No destructive actions.

03 · HOW IT WORKS

Scrapegraph Ai in three steps.

01Your users connect Scrapegraph AiThey add their Scrapegraph Ai api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “convert JSON to TOON Format” can wait for the user to approve.
03Any agent can actYour agent calls Scrapegraph Ai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('scrapegraph_ai', {
  read: 'allow',
  write: 'ask',        // toonify
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Scrapegraph Ai connects.

Users add their Scrapegraph Ai api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Scrapegraph Ai connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Scrapegraph Ai from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More web data and scraping apps.

Just One API288 actions

Apify183 actions

ALL WEB DATA AND SCRAPING APPS →

07 · FAQ

Scrapegraph Ai and Arc0, answered.

Q01

Can I use Scrapegraph Ai with Claude, ChatGPT or Cursor?

Yes. Connect Scrapegraph Ai to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Scrapegraph Ai actions you allow.

Q02

How do users connect Scrapegraph Ai?

Users add their Scrapegraph Ai api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Scrapegraph Ai actions can my agent take?

27 in total: 17 read, 10 write and 0 destructive, such as “convert JSON to TOON Format”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Scrapegraph Ai?

Yes. Allow read actions and deny writes in the Scrapegraph Ai policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Scrapegraph Ai too?

Yes. The same Scrapegraph Ai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Scrapegraph Ai into your agent.

Your users connect Scrapegraph Ai once, under your brand. Your agent gets 27 actions behind your policies, with every call on the record.

Connect Scrapegraph Ai Browse all apps →

Free to build · MCP + REST · Audit log on every plan