browser_snapshot
Capture an accessibility snapshot of the current page to get structured, text-based page content instead of relying on screenshots for analysis.
Instructions
Capture accessibility snapshot of the current page, this is better than screenshot
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "browser_snapshot"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| boxes | No | Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect) | |
| depth | No | Limit the depth of the snapshot tree | |
| target | No | Exact target element reference from the page snapshot, or a unique element selector | |
| session | No | Session id (default "default"). Each session is an isolated browser (own cookies, tabs) that runs in parallel with the others. Created on first use. | |
| filename | No | Save snapshot to a file instead of returning it in the response. Relative file names are resolved against the workspace root. |