Browser
browserRead
Read Browser Page
Read the current page of a browser session as markdown, plus key metadata (title, final URL, description).
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "read that page", and it calls browserRead.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"sessionId": "<sessionId>"
},
"name": "browserRead"
}Arguments
sessionIdstringrequiredThe browser session to read: the sessionId from browserOpen.
Returns
This dispatches a fresh read to the box AND returns the session's most recent snapshot; on the first read right after opening (or right after an action), the snapshot may still be landing: call…
Ask for it
The Cloud routes these requests to this verb.
- read that page
- what does the page say
- get the page content
- extract the article
Pair it with
The verbs that finish the job.
Questions
What does browserRead do?
Read the current page of a browser session as markdown, plus key metadata (title, final URL, description). It is one of the tools The Cloud MCP server gives every connected AI.
How do I use browserRead 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 "read that page", and it calls browserRead.
Is browserRead safe to let an AI call?
browserRead 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.