GetScreenshot is an MCP server published by com.getscreenshotapi, hosted at mcp.getscreenshotapi.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including capture_screenshot, render_html, compare_screenshots, capture_pdf, get_usage.
Screenshot web pages, render HTML and diff captures, with images sized for vision models.
54 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| url * | string | 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 | string | Browser language / Accept-Language, for example "de-DE". API default "en-US". |
| click | string | 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 | integer | 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 | integer | Viewport width in CSS pixels. API default 1280. Ignored when device is set. |
| cookie | object | 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 | string | 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. |
| device | string | 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 | string | Format of the stored file at screenshot_url. Inline images are always JPEG. |
| height | integer | Viewport height in CSS pixels. API default 800. Ignored when device is set. |
| return | string | "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). |
| element | string | 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 | integer | Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering. |
| custom_js | string | JavaScript run in the page before capture. |
| full_page | boolean | Capture the whole scrollable page instead of just the viewport. Tall pages are returned as several image slices and cost more tokens. |
| highlight | string | Keyword(s) to highlight on the page. |
| custom_css | string | CSS injected into the page before capture. |
| max_slices | integer | 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 | string | 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 | string | CSS selector(s) to hide (display:none) before capture, comma-separated, for example ".newsletter-popup, #ad-banner". |
| hide_chat_widgets | boolean | Hide common chat widgets (Intercom, Drift and similar). |
| full_page_strategy | integer | 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 | boolean | Hide common cookie-consent banners. Set false to keep them in the picture. |
| transparent_background | boolean | Keep the background transparent where the page sets none (PNG only). Inline images are flattened onto white. |
{
"name": "capture_screenshot",
"title": "Capture screenshot",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 8192,
"minLength": 1,
"description": "Absolute http(s) URL of the page, reachable from the public internet. localhost and private-network addresses cannot be captured; use render_html for local HTML."
},
"lang": {
"type": "string",
"maxLength": 35,
"minLength": 2,
"description": "Browser language / Accept-Language, for example \"de-DE\". API default \"en-US\"."
},
"click": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "CSS selector of an element to click once before the capture, for example to open a menu or dismiss a dialog. A selector that matches nothing makes the capture fail."
},
"scale": {
"type": "integer",
"maximum": 3,
"minimum": 1,
"description": "Device pixel ratio of the stored image: 1 (default), 2 (retina) or 3. Affects the file at screenshot_url; inline images are downscaled either way."
},
"width": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport width in CSS pixels. API default 1280. Ignored when device is set."
},
"cookie": {
"type": "object",
"required": [
"name",
"value"
],
"properties": {
"name": {
"type": "string",
"pattern": "^[^,;=\\s]+$",
"maxLength": 256,
"minLength": 1
},
"value": {
"type": "string",
"pattern": "^[^,;\\s]*$",
"maxLength": 4096
}
},
"description": "One cookie to set for the target host before loading, for example a feature flag or locale. Do not pass credentials or session tokens.",
"additionalProperties": false
},
"detail": {
"enum": [
"standard",
"high"
],
"type": "string",
"default": "standard",
"description": "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."
},
"device": {
"enum": [
"iphone5",
"iphone678",
"iphone678_plus",
"iphonex",
"iphone12",
"pixel2",
"pixel2_xl",
"ipad",
"ipadpro",
"hvga",
"wvga",
"dvga",
"wxga_v",
"xga",
"wxga_s",
"wxga_l",
"sxga",
"wsxga_plus"
],
"type": "string",
"description": "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": {
"enum": [
"png",
"jpeg"
],
"type": "string",
"default": "png",
"description": "Format of the stored file at screenshot_url. Inline images are always JPEG."
},
"height": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport height in CSS pixels. API default 800. Ignored when device is set."
},
"return": {
"enum": [
"image_and_url",
"url_only"
],
"type": "string",
"default": "image_and_url",
"description": "\"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)."
},
"element": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "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": {
"type": "integer",
"maximum": 20000,
"minimum": 0,
"description": "Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering."
},
"custom_js": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "JavaScript run in the page before capture."
},
"full_page": {
"type": "boolean",
"default": false,
"description": "Capture the whole scrollable page instead of just the viewport. Tall pages are returned as several image slices and cost more tokens."
},
"highlight": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Keyword(s) to highlight on the page."
},
"custom_css": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "CSS injected into the page before capture."
},
"max_slices": {
"type": "integer",
"default": 4,
"maximum": 10,
"minimum": 1,
"description": "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": {
"enum": [
"load",
"domcontentloaded",
"networkidle0",
"networkidle2"
],
"type": "string",
"description": "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": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "CSS selector(s) to hide (display:none) before capture, comma-separated, for example \".newsletter-popup, #ad-banner\"."
},
"hide_chat_widgets": {
"type": "boolean",
"default": false,
"description": "Hide common chat widgets (Intercom, Drift and similar)."
},
"full_page_strategy": {
"type": "integer",
"maximum": 3,
"minimum": 0,
"description": "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": {
"type": "boolean",
"default": true,
"description": "Hide common cookie-consent banners. Set false to keep them in the picture."
},
"transparent_background": {
"type": "boolean",
"default": false,
"description": "Keep the background transparent where the page sets none (PNG only). Inline images are flattened onto white."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"screenshot_url",
"origin_url",
"page_status",
"captured_at",
"format",
"original",
"images",
"total_slices",
"truncated",
"estimated_image_tokens",
"expires_in_days",
"warnings"
],
"properties": {
"format": {
"enum": [
"png",
"jpeg"
],
"type": "string",
"description": "Format of the stored file at screenshot_url."
},
"images": {
"type": "array",
"items": {
"type": "object",
"required": [
"index",
"y",
"width",
"height",
"estimated_tokens"
],
"properties": {
"y": {
"type": "number",
"description": "Top offset of this image within the downscaled capture, in the same pixels as width/height."
},
"index": {
"type": "number",
"description": "0-based position of the slice, top to bottom."
},
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"estimated_tokens": {
"type": "number",
"description": "Approximate vision tokens: ceil(width/28) * ceil(height/28)."
}
},
"additionalProperties": false
},
"description": "One entry per inline image, in the same order as the image blocks."
},
"original": {
"anyOf": [
{
"type": "object",
"required": [
"width",
"height"
],
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Pixel size of the stored image. Null if it could not be read."
},
"warnings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Things worth knowing about this result, for example an error status from the page."
},
"truncated": {
"type": "boolean",
"description": "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": {
"type": "string"
},
"captured_at": {
"type": [
"string",
"null"
],
"description": "ISO 8601 UTC time of the capture."
},
"page_status": {
"type": [
"number",
"null"
],
"description": "HTTP status the page answered with. 400 or above usually means an error page was captured."
},
"total_slices": {
"type": "number",
"description": "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": {
"type": "string",
"description": "Full-resolution image. Public to anyone who has the link."
},
"expires_in_days": {
"type": "number",
"description": "Stored files are deleted after this many days."
},
"estimated_image_tokens": {
"type": "number",
"description": "Approximate total vision tokens of the inline images."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Capture screenshot",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Render an HTML string in a real browser and return a screenshot you can see. Use it to check a component, email or page you just wrote without deploying it, and to look at local work, since the capture service cannot reach localhost. The HTML is hosted at an unguessable temporary URL, captured like any page, deleted as soon as the capture returns, and the result has the same shape as capture_screenshot. Assets must be inlined or use absolute public URLs: relative paths and localhost URLs inside the HTML will not load unless the HTML sets <base href> to a public origin. The page runs in a sandbox without cookies or localStorage, so code that depends on them may render blank. Cookie-banner hiding is off for this tool, so the page renders exactly as written. Costs 1 screenshot of the monthly quota per call. Takes about 9-25 seconds. Do not put secrets in the HTML: the resulting image link is public to anyone who has it.
| Parameter | Type | Description |
|---|---|---|
| html * | string | The HTML document or fragment to render, at most 2 MB. Inline the CSS and JS it needs, or load them from absolute public URLs. Relative asset URLs only resolve if the HTML sets <base href>. |
| scale | integer | 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 | integer | Viewport width in CSS pixels. API default 1280. Ignored when device is set. |
| detail | string | 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. |
| device | string | 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. |
Visual diff of two pages or two existing screenshots. Use it to verify a change did what you intended and nothing else moved: before/after a deploy, staging vs production, or one page at two points in time. Each side is either `{url}` (captured now) or `{screenshot_url}` (an earlier GetScreenshot result, reused at no cost; it is checked before any capture is spent). To compare a page across a change, capture it first, make the change, then pass the earlier screenshot_url as `before` and the page url as `after`. Returns the percentage of changed pixels, the bounding box of the changed area, and a diff image: the after image dimmed, changed pixels in magenta, a red rectangle around the changed area. When nothing changed no image is attached. Costs 1 screenshot of the monthly quota per side given as `url` (0 to 2 per call). Both sides are captured with the same viewport options. Takes about 9-25 seconds when it captures. Limits: pages must be publicly reachable. At most the top 2,400 px are compared (at up to 1280 px wide); for a lower part of a long page, capture that part of both versions with capture_screenshot and `element`, then compare the two screenshot_url values. Animations, ads and rotating content show up as differences; hide them with hide_selectors.
| Parameter | Type | Description |
|---|---|---|
| after * | object | The "after" image. Provide exactly one of url or screenshot_url. |
| width | integer | Viewport width in CSS pixels. API default 1280. Ignored when device is set. |
| before * | object | The "before" image. Provide exactly one of url or screenshot_url. |
| device | string | 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. |
Save a public web page as an A4 PDF and return a link to the file. Use it when the user wants a document to keep, share or archive. The PDF is not shown to you; to look at a page use capture_screenshot. Costs 1 screenshot of the monthly quota per call, failed captures included. Takes about 9-25 seconds. The link is public to anyone who has it and expires in 30 days. Limits: the page must be reachable from the public internet (no localhost or private networks).
| Parameter | Type | Description |
|---|---|---|
| url * | string | 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. |
| wait_ms | integer | Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering. |
| custom_css | string | CSS injected before the PDF is made, for example print tweaks. |
| wait_until | string | 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 | string | CSS selector(s) to hide (display:none) before capture, comma-separated, for example ".newsletter-popup, #ad-banner". |
{
"name": "capture_pdf",
"title": "Capture PDF",
"description": "Save a public web page as an A4 PDF and return a link to the file. Use it when the user wants a document to keep, share or archive. The PDF is not shown to you; to look at a page use capture_screenshot. Costs 1 screenshot of the monthly quota per call, failed captures included. Takes about 9-25 seconds. The link is public to anyone who has it and expires in 30 days. Limits: the page must be reachable from the public internet (no localhost or private networks).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 8192,
"minLength": 1,
"description": "Absolute http(s) URL of the page, reachable from the public internet. localhost and private-network addresses cannot be captured; use render_html for local HTML."
},
"wait_ms": {
"type": "integer",
"maximum": 20000,
"minimum": 0,
"description": "Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering."
},
"custom_css": {
"type": "string",
"maxLength": 20000,
"minLength": 1,
"description": "CSS injected before the PDF is made, for example print tweaks."
},
"wait_until": {
"enum": [
"load",
"domcontentloaded",
"networkidle0",
"networkidle2"
],
"type": "string",
"description": "When the page counts as loaded. API default \"networkidle2\". Use \"domcontentloaded\" for heavy or slow sites (fastest, most reliable); \"networkidle0\" waits for all network activity to stop."
},
"hide_selectors": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "CSS selector(s) to hide (display:none) before capture, comma-separated, for example \".newsletter-popup, #ad-banner\"."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"pdf_url",
"origin_url",
"page_status",
"captured_at",
"expires_in_days",
"warnings"
],
"properties": {
"pdf_url": {
"type": "string",
"description": "The PDF file. Public to anyone who has the link."
},
"warnings": {
"type": "array",
"items": {
"type": "string"
}
},
"origin_url": {
"type": "string"
},
"captured_at": {
"type": [
"string",
"null"
]
},
"page_status": {
"type": [
"number",
"null"
]
},
"expires_in_days": {
"type": "number"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Capture PDF",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Report how many screenshots the configured API key has used this month, the plan's monthly limit, how many are left and when the quota resets. Use it before a large batch of captures or when a capture fails with a quota error. This check itself costs 1 screenshot of the quota, so do not call it routinely.
No parameters.
{
"name": "get_usage",
"title": "Get usage",
"description": "Report how many screenshots the configured API key has used this month, the plan's monthly limit, how many are left and when the quota resets. Use it before a large batch of captures or when a capture fails with a quota error. This check itself costs 1 screenshot of the quota, so do not call it routinely.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"used",
"limit",
"remaining",
"percent_used",
"period",
"quota_restart_date",
"resets_on"
],
"properties": {
"used": {
"type": "number",
"description": "Screenshots used in the current period."
},
"limit": {
"type": "number",
"description": "Screenshots included per period on this plan."
},
"period": {
"type": "string"
},
"remaining": {
"type": "number"
},
"resets_on": {
"type": [
"string",
"null"
],
"description": "Date (UTC) the monthly quota next resets."
},
"percent_used": {
"type": "number"
},
"quota_restart_date": {
"type": [
"string",
"null"
],
"description": "`quotaRestartDate` exactly as the API reports it."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Get usage",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}GetScreenshot captures public web pages with a hosted headless browser and returns images sized for vision models. Use capture_screenshot to look at a live URL; pass `element` to look at one part of a page cheaply, and `full_page` only when you need the whole page. Use render_html to see HTML you have as a string (a component or page you just wrote); this is also the way to check local work, because the service cannot reach localhost or private networks. Use compare_screenshots to verify a visual change (before/after, staging vs production), capture_pdf for an A4 PDF link, and get_usage to check the remaining quota. Every capture uses one screenshot of the monthly quota, failed captures included, and takes about 9-25 seconds, so fix the input instead of retrying a failure unchanged. If a page fails to load, retry once with wait_until: "domcontentloaded". Captures are single shots of a page: there is no session, login flow or multi-step interaction.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| height | integer | Viewport height in CSS pixels. API default 800. Ignored when device is set. |
| return | string | "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). |
| element | string | 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 | integer | Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering. |
| full_page | boolean | Capture the whole scrollable page instead of just the viewport. Tall pages are returned as several image slices and cost more tokens. |
| max_slices | integer | 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). |
{
"name": "render_html",
"title": "Render HTML",
"description": "Render an HTML string in a real browser and return a screenshot you can see. Use it to check a component, email or page you just wrote without deploying it, and to look at local work, since the capture service cannot reach localhost. The HTML is hosted at an unguessable temporary URL, captured like any page, deleted as soon as the capture returns, and the result has the same shape as capture_screenshot. Assets must be inlined or use absolute public URLs: relative paths and localhost URLs inside the HTML will not load unless the HTML sets <base href> to a public origin. The page runs in a sandbox without cookies or localStorage, so code that depends on them may render blank. Cookie-banner hiding is off for this tool, so the page renders exactly as written. Costs 1 screenshot of the monthly quota per call. Takes about 9-25 seconds. Do not put secrets in the HTML: the resulting image link is public to anyone who has it.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"minLength": 1,
"description": "The HTML document or fragment to render, at most 2 MB. Inline the CSS and JS it needs, or load them from absolute public URLs. Relative asset URLs only resolve if the HTML sets <base href>."
},
"scale": {
"type": "integer",
"maximum": 3,
"minimum": 1,
"description": "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": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport width in CSS pixels. API default 1280. Ignored when device is set."
},
"detail": {
"enum": [
"standard",
"high"
],
"type": "string",
"default": "standard",
"description": "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."
},
"device": {
"enum": [
"iphone5",
"iphone678",
"iphone678_plus",
"iphonex",
"iphone12",
"pixel2",
"pixel2_xl",
"ipad",
"ipadpro",
"hvga",
"wvga",
"dvga",
"wxga_v",
"xga",
"wxga_s",
"wxga_l",
"sxga",
"wsxga_plus"
],
"type": "string",
"description": "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."
},
"height": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport height in CSS pixels. API default 800. Ignored when device is set."
},
"return": {
"enum": [
"image_and_url",
"url_only"
],
"type": "string",
"default": "image_and_url",
"description": "\"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)."
},
"element": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "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": {
"type": "integer",
"maximum": 20000,
"minimum": 0,
"description": "Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering."
},
"full_page": {
"type": "boolean",
"default": false,
"description": "Capture the whole scrollable page instead of just the viewport. Tall pages are returned as several image slices and cost more tokens."
},
"max_slices": {
"type": "integer",
"default": 4,
"maximum": 10,
"minimum": 1,
"description": "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)."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"screenshot_url",
"origin_url",
"page_status",
"captured_at",
"format",
"original",
"images",
"total_slices",
"truncated",
"estimated_image_tokens",
"expires_in_days",
"warnings"
],
"properties": {
"format": {
"enum": [
"png",
"jpeg"
],
"type": "string",
"description": "Format of the stored file at screenshot_url."
},
"images": {
"type": "array",
"items": {
"type": "object",
"required": [
"index",
"y",
"width",
"height",
"estimated_tokens"
],
"properties": {
"y": {
"type": "number",
"description": "Top offset of this image within the downscaled capture, in the same pixels as width/height."
},
"index": {
"type": "number",
"description": "0-based position of the slice, top to bottom."
},
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"estimated_tokens": {
"type": "number",
"description": "Approximate vision tokens: ceil(width/28) * ceil(height/28)."
}
},
"additionalProperties": false
},
"description": "One entry per inline image, in the same order as the image blocks."
},
"original": {
"anyOf": [
{
"type": "object",
"required": [
"width",
"height"
],
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Pixel size of the stored image. Null if it could not be read."
},
"warnings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Things worth knowing about this result, for example an error status from the page."
},
"truncated": {
"type": "boolean",
"description": "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": {
"type": "string"
},
"captured_at": {
"type": [
"string",
"null"
],
"description": "ISO 8601 UTC time of the capture."
},
"page_status": {
"type": [
"number",
"null"
],
"description": "HTTP status the page answered with. 400 or above usually means an error page was captured."
},
"total_slices": {
"type": "number",
"description": "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": {
"type": "string",
"description": "Full-resolution image. Public to anyone who has the link."
},
"expires_in_days": {
"type": "number",
"description": "Stored files are deleted after this many days."
},
"estimated_image_tokens": {
"type": "number",
"description": "Approximate total vision tokens of the inline images."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Render HTML",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}| height | integer | Viewport height in CSS pixels. API default 800. Ignored when device is set. |
| wait_ms | integer | Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering. |
| full_page | boolean | Capture whole pages instead of the viewport. Applies to sides given as url. |
| threshold | number | Per-pixel colour tolerance from 0 (any difference counts) to 1 (nothing counts). Default 0.1 ignores anti-aliasing noise. |
| wait_until | string | 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 | string | CSS selector(s) to hide in both captures. Use it to remove things that change on every load (ads, carousels, timestamps) so they do not show up as differences. |
{
"name": "compare_screenshots",
"title": "Compare screenshots",
"description": "Visual diff of two pages or two existing screenshots. Use it to verify a change did what you intended and nothing else moved: before/after a deploy, staging vs production, or one page at two points in time. Each side is either `{url}` (captured now) or `{screenshot_url}` (an earlier GetScreenshot result, reused at no cost; it is checked before any capture is spent). To compare a page across a change, capture it first, make the change, then pass the earlier screenshot_url as `before` and the page url as `after`. Returns the percentage of changed pixels, the bounding box of the changed area, and a diff image: the after image dimmed, changed pixels in magenta, a red rectangle around the changed area. When nothing changed no image is attached. Costs 1 screenshot of the monthly quota per side given as `url` (0 to 2 per call). Both sides are captured with the same viewport options. Takes about 9-25 seconds when it captures. Limits: pages must be publicly reachable. At most the top 2,400 px are compared (at up to 1280 px wide); for a lower part of a long page, capture that part of both versions with capture_screenshot and `element`, then compare the two screenshot_url values. Animations, ads and rotating content show up as differences; hide them with hide_selectors.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"before",
"after"
],
"properties": {
"after": {
"type": "object",
"properties": {
"url": {
"type": "string",
"maxLength": 8192,
"minLength": 1,
"description": "A public page URL to capture now (uses 1 screenshot of quota)."
},
"screenshot_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "The screenshot_url of an earlier GetScreenshot capture (uses no quota). Only GetScreenshot storage URLs are accepted."
}
},
"description": "The \"after\" image. Provide exactly one of url or screenshot_url.",
"additionalProperties": false
},
"width": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport width in CSS pixels. API default 1280. Ignored when device is set."
},
"before": {
"type": "object",
"properties": {
"url": {
"type": "string",
"maxLength": 8192,
"minLength": 1,
"description": "A public page URL to capture now (uses 1 screenshot of quota)."
},
"screenshot_url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "The screenshot_url of an earlier GetScreenshot capture (uses no quota). Only GetScreenshot storage URLs are accepted."
}
},
"description": "The \"before\" image. Provide exactly one of url or screenshot_url.",
"additionalProperties": false
},
"device": {
"enum": [
"iphone5",
"iphone678",
"iphone678_plus",
"iphonex",
"iphone12",
"pixel2",
"pixel2_xl",
"ipad",
"ipadpro",
"hvga",
"wvga",
"dvga",
"wxga_v",
"xga",
"wxga_s",
"wxga_l",
"sxga",
"wsxga_plus"
],
"type": "string",
"description": "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."
},
"height": {
"type": "integer",
"maximum": 10000,
"minimum": 1,
"description": "Viewport height in CSS pixels. API default 800. Ignored when device is set."
},
"wait_ms": {
"type": "integer",
"maximum": 20000,
"minimum": 0,
"description": "Extra wait in milliseconds after load, before the capture. API default 2000. Raise it for late animations or client-side rendering."
},
"full_page": {
"type": "boolean",
"default": false,
"description": "Capture whole pages instead of the viewport. Applies to sides given as url."
},
"threshold": {
"type": "number",
"default": 0.1,
"maximum": 1,
"minimum": 0,
"description": "Per-pixel colour tolerance from 0 (any difference counts) to 1 (nothing counts). Default 0.1 ignores anti-aliasing noise."
},
"wait_until": {
"enum": [
"load",
"domcontentloaded",
"networkidle0",
"networkidle2"
],
"type": "string",
"description": "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": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "CSS selector(s) to hide in both captures. Use it to remove things that change on every load (ads, carousels, timestamps) so they do not show up as differences."
}
},
"additionalProperties": false
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"changed_percent",
"changed_pixels",
"total_pixels",
"identical",
"threshold",
"bounding_box",
"size_changed",
"compared",
"before",
"after",
"images",
"total_slices",
"truncated",
"estimated_image_tokens",
"expires_in_days",
"warnings"
],
"properties": {
"after": {
"type": "object",
"required": [
"screenshot_url",
"origin_url",
"page_status",
"width",
"height"
],
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"origin_url": {
"type": [
"string",
"null"
],
"description": "Page that was captured; null when an existing screenshot was supplied."
},
"page_status": {
"type": [
"number",
"null"
]
},
"screenshot_url": {
"type": "string"
}
},
"additionalProperties": false
},
"before": {
"type": "object",
"required": [
"screenshot_url",
"origin_url",
"page_status",
"width",
"height"
],
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"origin_url": {
"type": [
"string",
"null"
],
"description": "Page that was captured; null when an existing screenshot was supplied."
},
"page_status": {
"type": [
"number",
"null"
]
},
"screenshot_url": {
"type": "string"
}
},
"additionalProperties": false
},
"images": {
"type": "array",
"items": {
"type": "object",
"required": [
"index",
"y",
"width",
"height",
"estimated_tokens"
],
"properties": {
"y": {
"type": "number",
"description": "Top offset of this image within the downscaled capture, in the same pixels as width/height."
},
"index": {
"type": "number",
"description": "0-based position of the slice, top to bottom."
},
"width": {
"type": "number"
},
"height": {
"type": "number"
},
"estimated_tokens": {
"type": "number",
"description": "Approximate vision tokens: ceil(width/28) * ceil(height/28)."
}
},
"additionalProperties": false
},
"description": "One entry per inline image, in the same order as the image blocks."
},
"compared": {
"type": "object",
"required": [
"width",
"height"
],
"properties": {
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"description": "Size both images were normalised to before comparing.",
"additionalProperties": false
},
"warnings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Things worth knowing about this result, for example an error status from the page."
},
"identical": {
"type": "boolean",
"description": "True when no compared pixel differs and both images have exactly the same width and height."
},
"threshold": {
"type": "number"
},
"truncated": {
"type": "boolean",
"description": "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."
},
"bounding_box": {
"anyOf": [
{
"type": "object",
"required": [
"x",
"y",
"width",
"height"
],
"properties": {
"x": {
"type": "number"
},
"y": {
"type": "number"
},
"width": {
"type": "number"
},
"height": {
"type": "number"
}
},
"additionalProperties": false
},
{
"type": "null"
}
],
"description": "Smallest rectangle containing all changed pixels, in comparison-image pixels. Null when nothing changed."
},
"size_changed": {
"type": "boolean",
"description": "True when the two images differ in size, for example the page got taller."
},
"total_pixels": {
"type": "number"
},
"total_slices": {
"type": "number",
"description": "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."
},
"changed_pixels": {
"type": "number"
},
"changed_percent": {
"type": "number",
"description": "Share of compared pixels that differ, 0-100."
},
"expires_in_days": {
"type": "number",
"description": "Stored files are deleted after this many days."
},
"estimated_image_tokens": {
"type": "number",
"description": "Approximate total vision tokens of the inline images."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Compare screenshots",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}