Screenshot API for AI agents
Screenshot API renders webpages or custom HTML into images, PDFs, or video, and supports bulk capture jobs for teams that need visuals at scale. 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 Screenshot API.
Render a webpage screenshot
Captures a single page as an image or PDF for a report, listing, or archive.
Check a bulk job's status
Looks up whether a bulk screenshot job has finished before downloading the results.
Download bulk results only when ready
Pulls the completed batch of screenshots only after the job status confirms it is done.
5 Screenshot API actions, graded by risk.
Every Screenshot API 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.
- screenshot_api.get_bulk_job_statusGet Bulk Job Status
- screenshot_api.download_bulk_resultsDownload Bulk Results
write
3Create and change things. Allow, or ask the user first.
- screenshot_api.create_bulk_csv_jobCreate Bulk CSV Job
- screenshot_api.create_bulk_json_jobCreate Bulk JSON Job
- screenshot_api.render_screenshotRender Screenshot
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Screenshot API in three steps.
- 01Your users connect Screenshot APIThey add their Screenshot API api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Bulk CSV Job” can wait for the user to approve.
- 03Any agent can actYour agent calls Screenshot API through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('screenshot_api', { read: 'allow', write: 'ask', // create_bulk_csv_job destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Screenshot API connects.
Users add their Screenshot API 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 API 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 Screenshot API from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Screenshot API and Arc0, answered.
Can I use Screenshot API with Claude, ChatGPT or Cursor?
Yes. Connect Screenshot API 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 API actions you allow.
How do users connect Screenshot API?
Users add their Screenshot API 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 Screenshot API actions can my agent take?
5 in total: 2 read, 3 write and 0 destructive, such as “create Bulk CSV Job”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Screenshot API?
Yes. Allow read actions and deny writes in the Screenshot API policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Screenshot API too?
Yes. The same Screenshot API connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Screenshot API into your agent.
Your users connect Screenshot API 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