Airtop for AI agents

Airtop provides cloud browsers and AI-driven automation for navigating sites, clicking through pages and extracting data. Developers use it to run browser workflows without local infrastructure. 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.

Web data and scrapingAPI keyMCP + RESTairtop.ai
AUDIT LOG · AIRTOPPOLICY: acme-support
09:41:07 · claude · u_8f2read
airtop.list_windows
List Windows✓ allowed · 212ms
09:41:08 · claude · u_8f2read
airtop.query_page
Query Page✓ allowed · 164ms
09:41:09 · claude · u_8f2write
airtop.create_window
Create Window✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
airtop.close_window
Close Window✕ blocked · policy: deny
EVERY AIRTOP CALL, ON THE RECORD
01 · USE CASES

What agents do in Airtop.

01

Query data from a page

Extract specific information from a live web page loaded in a cloud browser session.

02

Fill in a form field

Type text into a field on a page as part of an automated browser workflow.

03

Terminate a browser session

Close out a running cloud browser session once its task is done, freeing up the resource.

02 · ACTIONS

10 Airtop actions, graded by risk.

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

read

3

Look things up. Allowed by default.

  • airtop.query_page
    Query Page
  • airtop.list_windows
    List Windows
  • airtop.list_sessions
    List Sessions

write

5

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

  • airtop.create_window
    Create Window
  • airtop.create_session
    Create Session
  • airtop.type_text
    Type Text
  • airtop.click_element
    Click Element
  • airtop.navigate_window
    Navigate Window

destructive

2

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

  • airtop.close_window
    Close Window
  • airtop.terminate_session
    Terminate Session
03 · HOW IT WORKS

Airtop in three steps.

  1. 01Your users connect AirtopThey add their Airtop api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Window” can wait for the user, and “close Window” can be denied outright.
  3. 03Any agent can actYour agent calls Airtop 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('airtop', {
  read: 'allow',
  write: 'ask',        // create_window
  destructive: 'deny',  // close_window
})

# 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 Airtop connects.

Users add their Airtop 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 Airtop 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 Airtop from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Airtop and Arc0, answered.

Q01

Can I use Airtop with Claude, ChatGPT or Cursor?

Yes. Connect Airtop 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 Airtop actions you allow.

Q02

How do users connect Airtop?

Users add their Airtop 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 Airtop actions can my agent take?

10 in total: 3 read, 5 write and 2 destructive, such as “create Window”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Airtop?

Yes. Actions like “close Window” 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 Airtop too?

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

Get started

Plug Airtop into your agent.

Your users connect Airtop once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

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