browser_computer
Run one computer-use action from a model, and see the screen.
Runs ONE action exactly as a computer-use model's tool gives it, in Anthropic's shape ({action: "left_click", coordinate: [x, y]}) or OpenAI's ({type: "click", x, y, button}), on the session's browser page. Then it returns what happened and a screenshot.
Inputs
| Name | Type | Default | Allowed values | Description |
|---|---|---|---|---|
sessionIdrequired | string | – | – | The session's id, from session_create. |
actionrequired | object | – | – | The provider's action object, as the model wrote it. |
maxWidth | integer | – | – | Scale the screenshot down to at most this width (100 to 3840). The action's coordinates are then read in that screenshot's pixels. |
screenshot | boolean | true | – | false skips the screenshot. |
This tool works in a session with a browser. On a shell-only session (created with browser: false) it answers browser_disabled. See the three kinds of session.
sessionId is the id that session_create returned. The server keeps no default session. If that session is stopped, this tool resumes it first, as it was (a resume starts a machine again, and billing with it).
Example call
This is what an MCP client sends. You do not write it yourself: ask the model in plain words and it calls the tool.
{ "name": "browser_computer", "arguments": { "sessionId": "6c1f3c9e-1d2a-4f67-9b0e-1b2c3d4e5f60", "action": { "action": "left_click", "coordinate": [ 320, 240 ] }, "maxWidth": 1024 }}What it returns
A line saying what happened, the pointer, the scale, the page's title and URL, and the screenshot as an image.
Clicked at (400, 300)Pointer: (320, 240) · scale 0.8 · Example Domain — https://example.com/When a call fails, the result is marked as an error. Its text starts with the API’s error code, such as unauthorized or session_not_running, followed by its message.
Annotations
The server tells every client what this tool does to the world, so a client can decide what to ask you about before it runs.
| Annotation | Value |
|---|---|
title | Run a computer-use action |
readOnlyHint | false |
destructiveHint | false |
openWorldHint | true |
Good to know
- It acts on the browser page only, never on the machine's desktop.
- It is limited to 300 calls a minute per session, and screenshots share that limit with
browser_screenshot.
The same thing with the API
| Endpoint | Reference |
|---|---|
POST /v1/sessions/{id}/browser/computer | Run a computer-use action |
These docs describe a beta API. Endpoints, fields and SDK methods may change before general availability; breaking changes will be listed in the changelog.