Browser
browserAct
Act in Browser
Act on a browser session's current page: click an element, type text into a field, or press a key.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "click the login button", and it calls browserAct.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {
"action": "<action>",
"sessionId": "<sessionId>"
},
"name": "browserAct"
}Arguments
actionstringrequiredThe interaction: "click" (a target), "type" (text into a target), or "press" (a key like Enter).sessionIdstringrequiredThe browser session to act on: the sessionId from browserOpen.targetstringoptionalThe element to act on: a CSS selector (e.g. "#submit") or visible text. Required for click and type; omit for press.valuestringoptionalFor "type", the text to enter into the target. For "press", the key name (e.g. "Enter", "Escape"). Omit for click.
Returns
The registry does not declare a return shape.
Ask for it
The Cloud routes these requests to this verb.
- click the login button
- type my email into the field
- press Enter
- fill in that form field
Pair it with
The verbs that finish the job.
Questions
What does browserAct do?
Act on a browser session's current page: click an element, type text into a field, or press a key. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use browserAct 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 "click the login button", and it calls browserAct.
Is browserAct safe to let an AI call?
browserAct deletes or sends, and calling it again does not undo it, so a careful client confirms with you before it runs. 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.