Get started

Browserless for AI agents

Browserless runs headless browser automation in the cloud, letting a script render pages, capture screenshots, or generate PDFs without hosting Chrome itself. 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 BrowserlessSee the 7 actions ↓
Developer toolsAPI keyMCP + RESTbrowserless.io
AUDIT LOG · BROWSERLESSPOLICY: acme-support
09:41:07 · claude · u_8f2read
browserless.download_file
Download file using Puppeteer script✓ allowed · 212ms
09:41:08 · claude · u_8f2read
browserless.scrape_content
Scrape webpage content using CSS selectors✓ allowed · 164ms
09:41:09 · claude · u_8f2write
browserless.generate_pdf
Generate PDF from webpage✓ approved · approved by user
EVERY BROWSERLESS CALL, ON THE RECORD
01 · USE CASES

What agents do in Browserless.

01

Generate a PDF from a page

Render a live webpage as a PDF, useful for turning an invoice page into a file to send.

02

Capture a screenshot for review

Take a screenshot of a page before publishing changes, so someone can confirm it looks right.

03

Scrape page content by selector

Pull structured content off a page using CSS selectors instead of copying it out by hand.

02 · ACTIONS

7 Browserless actions, graded by risk.

Every Browserless 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.

  • browserless.download_file
    Download file using Puppeteer script
  • browserless.scrape_content
    Scrape webpage content using CSS selectors
  • browserless.fetch_html_content
    Fetch HTML Content

write

4

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

  • browserless.generate_pdf
    Generate PDF from webpage
  • browserless.take_screenshot
    Take Screenshot
  • browserless.execute_custom_function
    Execute Custom Function
  • browserless.unblock_protected_content
    Unblock Protected Content

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Browserless in three steps.

  1. 01Your users connect BrowserlessThey add their Browserless api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “generate PDF from webpage” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Browserless 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('browserless', {
  read: 'allow',
  write: 'ask',        // generate_pdf
  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 Browserless connects.

Users add their Browserless 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 Browserless 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 Browserless from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Browserless and Arc0, answered.

Q01

Can I use Browserless with Claude, ChatGPT or Cursor?

Yes. Connect Browserless 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 Browserless actions you allow.

Q02

How do users connect Browserless?

Users add their Browserless 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 Browserless actions can my agent take?

7 in total: 3 read, 4 write and 0 destructive, such as “generate PDF from webpage”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Browserless?

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

Q05

Can my own backend call Browserless too?

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

Get started

Plug Browserless into your agent.

Your users connect Browserless once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.

Connect BrowserlessBrowse all apps →

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