Screenshot.fyi for AI agents

Screenshot.fyi takes website screenshots through a single API call, giving developers a quick way to capture a page's current appearance. 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.

Developer toolsAPI keyMCP + RESTscreenshot.fyi
AUDIT LOG · SCREENSHOT.FYIPOLICY: acme-support
09:41:09 · claude · u_8f2write
screenshot_fyi.take_screenshot
Take Screenshot✓ approved · approved by user
EVERY SCREENSHOT.FYI CALL, ON THE RECORD
01 · USE CASES

What agents do in Screenshot.fyi.

01

Take a screenshot of a URL

Captures the current rendered appearance of a specific webpage for a report or record.

02

Capture a page before a change

Takes a screenshot of a page's current state so it can be compared against a later version.

03

Confirm the target URL before capture

Checks the correct URL is set before spending an API call capturing the wrong page.

02 · ACTIONS

1 Screenshot.fyi actions, graded by risk.

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

read

0

Look things up. Allowed by default.

  • No read actions.

write

1

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

  • screenshot_fyi.take_screenshot
    Take Screenshot

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Screenshot.fyi in three steps.

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

Users add their Screenshot.fyi 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 Screenshot.fyi 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 Screenshot.fyi from any agent.

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

Screenshot.fyi and Arc0, answered.

Q01

Can I use Screenshot.fyi with Claude, ChatGPT or Cursor?

Yes. Connect Screenshot.fyi 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 Screenshot.fyi actions you allow.

Q02

How do users connect Screenshot.fyi?

Users add their Screenshot.fyi 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 Screenshot.fyi actions can my agent take?

1 in total: 0 read, 1 write and 0 destructive, such as “take Screenshot”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Screenshot.fyi?

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

Q05

Can my own backend call Screenshot.fyi too?

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

Get started

Plug Screenshot.fyi into your agent.

Your users connect Screenshot.fyi once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

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