ScreenshotOne for AI agents
ScreenshotOne is a screenshot API for developers that renders website screenshots, including animated captures, without needing to run browser 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 ScreenshotOne.
Take a screenshot of a webpage
Captures a static image of a target page for use in a report or preview.
Take a batch of screenshots
Captures screenshots for a list of URLs in one bulk request instead of one at a time.
Check usage before a large batch
Reads current API usage so a large bulk screenshot job stays within the account's limit.
5 ScreenshotOne actions, graded by risk.
Every ScreenshotOne action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- screenshotone.get_usageGet Usage
- screenshotone.list_devicesList Devices
write
3Create and change things. Allow, or ask the user first.
- screenshotone.take_screenshotTake Screenshot
- screenshotone.take_bulk_screenshotsTake Bulk Screenshots
- screenshotone.take_animated_screenshotTake Animated Screenshot
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
ScreenshotOne in three steps.
- 01Your users connect ScreenshotOneThey add their ScreenshotOne api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “take Screenshot” can wait for the user to approve.
- 03Any agent can actYour agent calls ScreenshotOne through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('screenshotone', { 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
How ScreenshotOne connects.
Users add their ScreenshotOne 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 ScreenshotOne 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 ScreenshotOne from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
ScreenshotOne and Arc0, answered.
Can I use ScreenshotOne with Claude, ChatGPT or Cursor?
Yes. Connect ScreenshotOne 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 ScreenshotOne actions you allow.
How do users connect ScreenshotOne?
Users add their ScreenshotOne 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 ScreenshotOne actions can my agent take?
5 in total: 2 read, 3 write and 0 destructive, such as “take Screenshot”. Your policies decide which of them each agent may call.
Can I make my agent read-only in ScreenshotOne?
Yes. Allow read actions and deny writes in the ScreenshotOne policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call ScreenshotOne too?
Yes. The same ScreenshotOne connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug ScreenshotOne into your agent.
Your users connect ScreenshotOne once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan