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.
What agents do in Airtop.
Query data from a page
Extract specific information from a live web page loaded in a cloud browser session.
Fill in a form field
Type text into a field on a page as part of an automated browser workflow.
Terminate a browser session
Close out a running cloud browser session once its task is done, freeing up the resource.
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
3Look things up. Allowed by default.
- airtop.query_pageQuery Page
- airtop.list_windowsList Windows
- airtop.list_sessionsList Sessions
write
5Create and change things. Allow, or ask the user first.
- airtop.create_windowCreate Window
- airtop.create_sessionCreate Session
- airtop.type_textType Text
- airtop.click_elementClick Element
- airtop.navigate_windowNavigate Window
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- airtop.close_windowClose Window
- airtop.terminate_sessionTerminate Session
Airtop in three steps.
- 01Your users connect AirtopThey add their Airtop api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Window” can wait for the user, and “close Window” can be denied outright.
- 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.
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
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
Use Airtop from any agent.
More web data and scraping apps.
Airtop and Arc0, answered.
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.
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.
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.
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.
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.
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