Capture screenshot
capture_screenshotCapture a public web page as a full-resolution image and inline JPEGs for vision models, so you can inspect live sites, verify deployed changes, or check mobile layouts.
Instructions
Capture a public web page as an image you can see. Renders the URL in a hosted headless Chromium and returns a link to the full-resolution image plus inline JPEG images sized for vision models. Use it to look at a live page, verify a deployed change, check a design on a phone preset, or read content that needs JavaScript to render. By default it captures the 1280x800 viewport (one image, about 1,300 image tokens). Pass element to capture one part of the page, or full_page: true for the whole page; tall captures come back as up to max_slices slices from the top. Costs 1 screenshot of the monthly quota per call, failed captures included. Takes about 9-25 seconds. Limits: the page must be reachable from the public internet (no localhost or private networks: use render_html for local HTML). One shot per call, no login flows or multi-step interaction. Sites with aggressive bot protection may refuse headless browsers.
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": "capture_screenshot"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL of the page, reachable from the public internet. localhost and private-network addresses cannot be captured; use render_html for local HTML. | |
| lang | No | Browser language / Accept-Language, for example "de-DE". API default "en-US". | |
| click | No | CSS selector of an element to click once before the capture, for example to open a menu or dismiss a dialog. A selector that matches nothing makes the capture fail. | |
| scale | No | Device pixel ratio of the stored image: 1 (default), 2 (retina) or 3. Affects the file at screenshot_url; inline images are downscaled either way. | |
| width | No | Viewport width in CSS pixels. API default 1280. Ignored when device is set. | |
| cookie | No | One cookie to set for the target host before loading, for example a feature flag or locale. Do not pass credentials or session tokens. | |
| detail | No | Size of the inline images. "standard": at most 1280 px wide, about 1,568 tokens per image. "high": at most 1920 px wide, about 4,784 tokens per image; use it only to read small text. | standard |
| device | No | Device preset: sets the viewport and, for phones, a mobile user agent. Overrides width and height. iphone* and pixel* are phones, ipad* are tablets, the rest are fixed desktop sizes. | |
| format | No | Format of the stored file at screenshot_url. Inline images are always JPEG. | png |
| height | No | Viewport height in CSS pixels. API default 800. Ignored when device is set. | |
| return | No | "image_and_url" attaches the images. "url_only" returns just the link and sizes, for when you need the file but do not need to look at it (uses no image tokens). | image_and_url |
| element | No | CSS selector of one element to capture, for example "#pricing" or "main .hero". Cheapest way to look at one part of a page. A selector that matches nothing makes the capture fail (and still uses quota). | |
| wait_ms | No | Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering. | |
| custom_js | No | JavaScript run in the page before capture. | |
| full_page | No | Capture the whole scrollable page instead of just the viewport. Tall pages are returned as several image slices and cost more tokens. | |
| highlight | No | Keyword(s) to highlight on the page. | |
| custom_css | No | CSS injected into the page before capture. | |
| max_slices | No | Maximum number of inline images. A tall capture is cut into slices from the top; slices beyond this are left out and reported as truncated. Slices are also left out if the inline images would exceed about 1.5 MB in total (4 MB at high detail). | |
| wait_until | No | When the page counts as loaded. API default "networkidle2". Use "domcontentloaded" for heavy or slow sites (fastest, most reliable); "networkidle0" waits for all network activity to stop. | |
| hide_selectors | No | CSS selector(s) to hide (display:none) before capture, comma-separated, for example ".newsletter-popup, #ad-banner". | |
| hide_chat_widgets | No | Hide common chat widgets (Intercom, Drift and similar). | |
| full_page_strategy | No | Full-page capture strategy 0-3 (default 0). Try another value if a full_page capture renders badly (missing sections, repeated headers). | |
| hide_cookie_banners | No | Hide common cookie-consent banners. Set false to keep them in the picture. | |
| transparent_background | No | Keep the background transparent where the page sets none (PNG only). Inline images are flattened onto white. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| format | Yes | Format of the stored file at screenshot_url. | |
| images | Yes | One entry per inline image, in the same order as the image blocks. | |
| original | Yes | Pixel size of the stored image. Null if it could not be read. | |
| warnings | Yes | Things worth knowing about this result, for example an error status from the page. | |
| truncated | Yes | True when images were requested and some slices were left out, because of max_slices or the inline size limit. Always false with return: "url_only", where no image is attached by request. | |
| origin_url | Yes | ||
| captured_at | Yes | ISO 8601 UTC time of the capture. | |
| page_status | Yes | HTTP status the page answered with. 400 or above usually means an error page was captured. | |
| total_slices | Yes | How many slices the whole image needs at this detail level, whether or not they are attached. With return: "url_only" this is how many a normal call would produce. | |
| screenshot_url | Yes | Full-resolution image. Public to anyone who has the link. | |
| expires_in_days | Yes | Stored files are deleted after this many days. | |
| estimated_image_tokens | Yes | Approximate total vision tokens of the inline images. |