Website Screenshot from a URL · MrScraper

Request a website screenshot from one URL. Choose the full scroll height or the page top and relevant loading conditions, then inspect any returned image for layout, visible content and access barriers before using it in a report.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Reuse my existing Toolmu connection; if setup is needed, follow https://toolmu.com/SKILL.md. Read get_tool for capture-page-screenshot-mrscraper and verify Tool ID b3a92b73-2aa9-4a61-9a00-b1c1555e22a6. Check current execution availability, identity, balance, budget and maximumCredits in the same environment. Explain the current spending ceiling and proceed only within my established authorization and budget; if the ceiling exceeds that budget, do not submit. Ask only for missing required information: the complete page URL. Put it in body.url. For this example, set body.screenshot to full; the placeholder is not a URL or a default. Add only requested supported options: super, geoCode, timeout, waitUntil, proxyCountry or waitForSelector. Preserve false and supplied values. Use the documented enums and bounds, and set important choices explicitly rather than assuming description-only defaults are injected. Do not add viewport, device, image-format, authentication, recording, HTML or batch inputs. Use one persisted idempotency key and a maxCredits bound. If an original submission or run is unresolved, inspect that same request/run instead of automatically submitting a replacement. Report the actual execution outcome and confirmed charge; explicitly identify an unconfirmed submission or charge rather than treating it as zero. Use only actual returned image material, identify the URL and requested capture/loading context, and distinguish visible observations from interpretation. Do not infer complete hidden content, successful authentication, precise device matching or current underlying data from the image.

Task:
Take a full-page screenshot of [paste the page link]. Describe only what is visible in the returned image, and note if a sign-in or access message blocks the page.

Paste into your connected AI's conversation.

Connection guide

Up to 120 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

MrScraper

Website Screenshot from a URL · MrScraper

You receive

A visual capture request for the supplied web page through MrScraper. Use any returned screenshot to review the visible page state, share a layout reference or investigate an unexpected page view. Keep the URL, chosen area and loading settings with the image so readers can understand its scope.

Start with your task

Take a full-page screenshot of [paste the page link]. Describe only what is visible in the returned image, and note if a sign-in or access message blocks the page.

What to know

The image depends on what the supplier can load and render for that request. Full-page capture does not establish all hidden, paginated or delayed content. Regional settings do not guarantee a particular visitor experience; login access, exact device dimensions and image format are not selectable here. A screenshot alone does not establish current underlying data or a reproducible pixel-for-pixel view.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Screenshot request`body`	`object`	Required	Required object containing the page URL and any chosen supported options. A screenshot request covers that page, with full or top as the capture area. Required fields `url`
Page URL`body.url`	`string`	Required	Required complete page URL including http:// or https://. Use the exact page you want to inspect; this request has no URL list or site-wide crawl input. Format `uri`
Additional access resources`body.super`	`boolean`	Optional	Optional boolean for the supplier's more resource-intensive access mode on difficult pages. Its description mentions real-device routing and false as the default; it does not guarantee bypassing access barriers or successful capture.
Page-loading country`body.geoCode`	`string`	Optional	Optional two-character country code describing where the page is loaded from. The supplier describes us as the default. It does not establish the exact regional content, visitor identity or page language. Minimum length `2` Maximum length `2`
Loading timeout (seconds)`body.timeout`	`integer`	Optional	Optional integer from 1 to 300 seconds for the page-loading wait. The supplier describes 300 as the default. A longer limit allows more waiting but does not prove that loading or capture succeeded. Minimum `1` Maximum `300`
Navigation completion condition`body.waitUntil`	`string`	Optional	Optional choice: domcontentloaded, load, networkidle0 or networkidle2. The supplier describes domcontentloaded as the default and networkidle0 as a slower, more thorough wait. Choose for the page; no value guarantees every dynamic element is ready. Options `domcontentloaded, load, networkidle0, networkidle2`
Screenshot area`body.screenshot`	`string`	Optional	Optional choice: full for the entire scroll height, or top for the visible viewport at the top of the page. The supplier describes full as the default. Set it explicitly when scope matters; full does not prove complete hidden or delayed content. Options `full, top`
Proxy exit country`body.proxyCountry`	`string`	Optional	Optional two-character country code for the proxy exit. The supplier describes us as the default. This is distinct from geoCode and is not a device, authentication or guaranteed localization setting. Minimum length `2` Maximum length `2`
Wait for an element`body.waitForSelector`	`string`	Optional	Optional nonempty CSS selector. Requests waiting until a matching element appears in the DOM for delayed content. Provide a selector you know is relevant; existence does not certify visibility or a fully rendered page. Minimum length `1`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "url"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "Full URL to scrape, including the http:// or https:// scheme."
        },
        "super": {
          "type": "boolean",
          "description": "Route through real devices to bypass hard anti-bot protection. Uses more upstream resources, so runs consume more tokens. Default false."
        },
        "geoCode": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two-letter country code to load the page from (default 'us')."
        },
        "timeout": {
          "type": "integer",
          "maximum": 300,
          "minimum": 1,
          "description": "Maximum seconds to wait for the page to fully load (default 300)."
        },
        "waitUntil": {
          "enum": [
            "domcontentloaded",
            "load",
            "networkidle0",
            "networkidle2"
          ],
          "type": "string",
          "description": "When the browser considers navigation complete (browser rendering only). 'networkidle0' is the most thorough but slowest. Default 'domcontentloaded'."
        },
        "screenshot": {
          "enum": [
            "full",
            "top"
          ],
          "type": "string",
          "description": "Capture area: 'full' for the entire scroll height (default), 'top' for the visible viewport only."
        },
        "proxyCountry": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two-letter country code of the proxy exit (default 'us')."
        },
        "waitForSelector": {
          "type": "string",
          "minLength": 1,
          "description": "Wait until this CSS selector appears in the DOM before extracting — for content that loads after the initial page."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

The request requires body and body.url. Supply a complete URL including http:// or https://. The screenshot option accepts full for the entire scroll height or top for the visible viewport at the top of the page. Choose the area explicitly when it matters to your review.

waitUntil accepts domcontentloaded, load, networkidle0 or networkidle2. These select a navigation completion condition; they do not certify that every dynamic component is ready. timeout is an integer from 1 to 300 seconds. waitForSelector accepts a nonempty CSS selector and requests waiting for a matching element to appear in the DOM.

geoCode and proxyCountry each accept a two-character country code: the former describes the page-loading country and the latter the proxy exit country. The optional super boolean requests the supplier's more resource-intensive access mode for difficult pages. These controls do not guarantee a particular regional page, logged-in view or successful access.

The supplier describes full, domcontentloaded, 300 seconds, us and false as defaults for the relevant options. Set choices explicitly when you rely on them. This Tool has no viewport size, device preset, credentials, image-format, recording or batch input; broader supplier screenshot documentation also covers controls outside this request.

Interpret any returned image as the page state actually captured under the selected conditions. Keep useful source and capture context when supplied. Image delivery and format depend on the actual response. A visible price, banner or layout is an observation from that capture, while hidden records, complete page text and present-day underlying data require separate evidence.

MrScraper screenshot capture guidance

MrScraper screenshot API reference — broader supplier controls

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

full describes the scroll height of the requested page. It does not cover linked pages or establish hidden panels, additional pagination or every delayed component. Review the actual image against the page area you needed.

Website Screenshot from a URL · MrScraper

Website Screenshot from a URL · MrScraper

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page and area to capture

Provide the page link

Describe only what the image shows

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose the page and area to capture

Provide the page link

Describe only what the image shows

Questions about this tool.

Does full capture every part of a website?

Which waiting option should I choose for delayed content?

Will the screenshot match my phone or logged-in browser?

Can the image establish page text, prices or underlying records?

Can I choose PNG, JPEG, image size or a recording?

How should I compare captures taken at different times?