Take screenshot
take_screenshotRead-only
Capture the page, viewport, or a single element as an image to verify layout, compare visual changes, or extract text that exists only inside images.
Instructions
Capture the page, the viewport or a single element as an image.
Do NOT use this to read a page. take_snapshot gives you the same content as searchable text, is dramatically smaller, and yields the uids every interaction tool needs. Use a screenshot only when you genuinely need pixels: layout and styling checks, visual regression, or text that exists only inside an image.
Element capture needs a uid from the current snapshot. Without file_path the image is returned inline as a base64 data URL.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| uid | No | Capture just this element, using a uid from the most recent take_snapshot. Cannot be combined with full_page. Empty string captures the page. | |
| format | No | Image format. "png" is lossless and the default; "jpeg" or "webp" with a quality setting are far smaller, which matters for full-page captures. | png |
| quality | No | Compression quality from 1 to 100, for jpeg and webp only. Ignored for png. 0 leaves Chrome's default. | |
| file_path | No | Write the image to this local path. Omit to get a base64 data URL inline in the response — that is expensive, so prefer a file for full-page or high-DPR captures. | |
| full_page | No | Capture the whole scrollable page rather than just the visible viewport. Cannot be combined with `uid`. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |