1. Docs
2. /
3. Tool reference
4. /
5. Browser
6. /
7. browserScreenshot

Browser

browserScreenshot

Screenshot Browser Page

Capture a screenshot of a browser session's current page.

writeexternal

Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "screenshot that page", and it calls browserScreenshot.

Example call

The MCP tools/call params, with the required arguments only.

{
  "arguments": {
    "sessionId": "<sessionId>"
  },
  "name": "browserScreenshot"
}

Arguments

• proofActionIdstringoptionalThe proofActionId from an earlier pending call. Pass it to check that same screenshot without dispatching another capture.
• sessionIdstringrequiredThe browser session to screenshot, from browserOpen.

Returns

The first call dispatches a capture and returns proofActionId plus proofSessionId; if pending is true, call again with the same proofActionId to check that receipt without starting another capture.

Ask for it

The Cloud routes these requests to this verb.

• screenshot that page
• grab a picture of the page
• capture the browser

Pair it with

The verbs that finish the job.

• browserOpen
• browserRead

Questions

• What does browserScreenshot do?

  Capture a screenshot of a browser session's current page. It is one of the tools The Cloud MCP server gives every connected AI.

• How do I use browserScreenshot from Claude or ChatGPT?

  Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "screenshot that page", and it calls browserScreenshot.

• Is browserScreenshot safe to let an AI call?

  browserScreenshot changes your workspace. What an AI creates is Private until you share it. It reaches a system outside The Cloud on your behalf.

Connect

One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.