Scrape Do for AI agents

Scrape.do is a web scraping API that routes requests through rotating proxies and headless browsers to pull data from pages that block ordinary scrapers. 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 Scrape Do See the 16 actions ↓

Web data and scrapingAPI keyMCP + RESTscrape.do

AUDIT LOG · SCRAPE DOPOLICY: acme-support

09:41:07 · claude · u_8f2read

scrape_do.list_async_jobs

List Asynchronous Scraping Jobs✓ allowed · 212ms

09:41:08 · claude · u_8f2read

scrape_do.get_page

Scrape webpage using scrape.do✓ allowed · 164ms

09:41:09 · claude · u_8f2write

scrape_do.create_async_job

Create Async Scraping Job✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

scrape_do.cancel_async_job

Cancel Async Job✕ blocked · policy: deny

EVERY SCRAPE DO CALL, ON THE RECORD

01 · USE CASES

What agents do in Scrape Do.

Scrape a webpage on demand

Fetches the rendered HTML or JSON of a target webpage through a rotating residential or data-center proxy.

Check account usage before a big job

Reads current account credit and request usage before kicking off a large async scraping job.

Cancel a running async job

Stops an in-progress asynchronous scraping job once it is no longer needed instead of letting it finish.

02 · ACTIONS

16 Scrape Do actions, graded by risk.

Every Scrape Do 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.

scrape_do.get_page
Scrape webpage using scrape.do
scrape_do.get_async_job
Get Async Job Details
scrape_do.search_amazon
Search Amazon products
scrape_do.get_async_task
Get Async Task Result
scrape_do.list_async_jobs
List Asynchronous Scraping Jobs
scrape_do.get_account_info
Get Account Information
scrape_do.get_amazon_offers
Get Amazon Product Offers
scrape_do.get_amazon_product
Get Amazon product details
scrape_do.get_amazon_raw_html
Get Amazon raw HTML
scrape_do.get_async_account_info
Get Async API Account Information
scrape_do.scrape_url_post
Scrape URL using POST method

write

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

scrape_do.create_async_job
Create Async Scraping Job
scrape_do.proxy_mode
Use Scrape.do Proxy Mode
scrape_do.set_regional_geo_code
Set Regional Geolocation for Scraping

destructive

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

scrape_do.cancel_async_job
Cancel Async Job
scrape_do.set_block_urls
Block specific URLs during scraping

03 · HOW IT WORKS

Scrape Do in three steps.

01Your users connect Scrape DoThey add their Scrape Do api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create Async Scraping Job” can wait for the user, and “cancel Async Job” can be denied outright.
03Any agent can actYour agent calls Scrape Do 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('scrape_do', {
  read: 'allow',
  write: 'ask',        // create_async_job
  destructive: 'deny',  // cancel_async_job
})

# 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 Scrape Do connects.

Users add their Scrape Do 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 Scrape Do 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 Scrape Do 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

Scrape Do and Arc0, answered.

Q01

Can I use Scrape Do with Claude, ChatGPT or Cursor?

Yes. Connect Scrape Do 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 Scrape Do actions you allow.

Q02

How do users connect Scrape Do?

Users add their Scrape Do 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 Scrape Do actions can my agent take?

16 in total: 11 read, 3 write and 2 destructive, such as “create Async Scraping Job”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Scrape Do?

Yes. Actions like “cancel Async Job” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Scrape Do too?

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

Get started

Plug Scrape Do into your agent.

Your users connect Scrape Do once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Connect Scrape Do Browse all apps →

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