Cloudflare Browser Rendering for AI agents

Cloudflare Browser Rendering runs headless browsers on Cloudflare's network, letting a workflow capture screenshots, generate PDFs, or scrape page content. 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 Cloudflare Browser Rendering See the 4 actions ↓

Web data and scrapingAPI keyMCP + RESTcloudflare.com

AUDIT LOG · CLOUDFLARE BROWSER RENDERINGPOLICY: acme-support

09:41:07 · claude · u_8f2read

cloudflare_browser_rendering.list_accounts

List Accounts✓ allowed · 212ms

09:41:08 · claude · u_8f2read

cloudflare_browser_rendering.scrape_html_elements

Scrape HTML Elements✓ allowed · 164ms

09:41:09 · claude · u_8f2write

cloudflare_browser_rendering.capture_screenshot

Capture Screenshot✓ approved · approved by user

EVERY CLOUDFLARE BROWSER RENDERING CALL, ON THE RECORD

01 · USE CASES

What agents do in Cloudflare Browser Rendering.

Capture a page screenshot

Capture a screenshot of a live webpage for archiving or visual comparison.

Scrape specific page elements

Scrape targeted HTML elements off a page instead of pulling the entire document.

Take a full webpage snapshot

Take a full snapshot of a webpage's rendered content for later reference.

02 · ACTIONS

4 Cloudflare Browser Rendering actions, graded by risk.

Every Cloudflare Browser Rendering 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.

cloudflare_browser_rendering.list_accounts
List Accounts
cloudflare_browser_rendering.scrape_html_elements
Scrape HTML Elements

write

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

cloudflare_browser_rendering.capture_screenshot
Capture Screenshot
cloudflare_browser_rendering.take_webpage_snapshot
Take Webpage Snapshot

destructive

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

No destructive actions.

03 · HOW IT WORKS

Cloudflare Browser Rendering in three steps.

01Your users connect Cloudflare Browser RenderingThey add their Cloudflare Browser Rendering api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “capture Screenshot” can wait for the user to approve.
03Any agent can actYour agent calls Cloudflare Browser Rendering 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('cloudflare_browser_rendering', {
  read: 'allow',
  write: 'ask',        // capture_screenshot
  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 Cloudflare Browser Rendering connects.

Users add their Cloudflare Browser Rendering 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 Cloudflare Browser Rendering 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 Cloudflare Browser Rendering 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

Cloudflare Browser Rendering and Arc0, answered.

Q01

Can I use Cloudflare Browser Rendering with Claude, ChatGPT or Cursor?

Yes. Connect Cloudflare Browser Rendering 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 Cloudflare Browser Rendering actions you allow.

Q02

How do users connect Cloudflare Browser Rendering?

Users add their Cloudflare Browser Rendering 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 Cloudflare Browser Rendering actions can my agent take?

4 in total: 2 read, 2 write and 0 destructive, such as “capture Screenshot”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Cloudflare Browser Rendering?

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

Q05

Can my own backend call Cloudflare Browser Rendering too?

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

Get started

Plug Cloudflare Browser Rendering into your agent.

Your users connect Cloudflare Browser Rendering once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.

Connect Cloudflare Browser Rendering Browse all apps →

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