crawl_screenshot
Take a screenshot of any webpage with customizable device, mode, and viewport settings. Optionally persist the underlying HTML to cloud storage.
Instructions
Take a screenshot of a webpage. Pass store=true to persist the underlying HTML page to Cloud Storage (the screenshot itself is not stored and is still returned as an ephemeral screenshot_url).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "crawl_screenshot"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to screenshot | |
| mode | No | Screenshot mode (default: fullpage) | |
| store | No | Persist the underlying HTML page to Cloud Storage. The screenshot itself is not stored; only RID + metadata + screenshot_url are returned (no image download). Storage is scoped to the JS token — use_js_token=true is required when retrieving it later. | |
| width | No | Maximum width in pixels (only with mode=viewport) | |
| device | No | Device type for screenshot | |
| height | No | Maximum height in pixels (only with mode=viewport) | |
| page_wait | No | Wait time before taking screenshot |