urlbox/urlbox-mcp-server

urlbox/urlbox-mcp-server

от urlbox
MCP-сервер для Urlbox Screenshot API: делайте скриншоты, PDF, извлекайте HTML и markdown с любых сайтов. Идеален для AI-ассистентов, чтобы захватывать страницы без рекламы и куки-баннеров.

Urlbox MCP Server

image

MCP server for the Urlbox Screenshot API. Enables your client to take screenshots, generate PDFs, extract HTML/markdown, and more from websites.

Visit Urlbox for more information, and have a read of our docs or chat with your LLM post install to get a good understanding of its options and capabilities.

MCP Badge

Setup

  1. Install dependencies and build:

    npm install
    npm run build
    
  2. Get Urlbox API credentials:

  3. Set environment variables:

claude_desktop_config.json

{
  "mcpServers": {
    "screenshot": {
      "command": "npx",
      "args": ["-y", "@urlbox/screenshot-mcp"],
      "env": {
        "SECRET_KEY": "your_api_key_here"
      }
    }
  }
}

Usage

The server provides a render tool that can:

  • Take screenshots in multiple formats (PNG, PDF, MP4 and more)
  • Convert pages to HTML, markdown
  • Extract metadata and cookies
  • Save files locally to your downloads with store_renders: true

Claude will automatically use this when you ask it to screenshot websites or convert web content.

download

Берёт все URL рендеров из любого ответа Urlbox, которые ещё не были загружены, и сохраняет их в файловую систему пользователя.

Берёт все URL рендеров из любого ответа Urlbox, которые ещё не были загружены, и сохраняет их в файловую систему пользователя.

Параметры

  • renderUrlstring

    Main render URL to download

  • htmlUrlstring

    HTML URL to download

  • markdownUrlstring

    Markdown URL to download

  • metadataUrlstring

    Metadata JSON URL to download

  • mhtmlUrlstring

    MHTML URL to download

  • originalOptionsobjectобязательный

    Original options used for the render to help with filename generation

render

Использует POST API Urlbox.com для продвинутого рендеринга с боковыми рендерами. Скачивание на компьютер через store_renders: true. Идеально подходит для: использования множества опций, конвертации сайтов в HTML/PDF/markdown, извлечения метаданных, сохранения куки, рендеринга кастомного HTML/CSS/JS и одновременной генерации нескольких выходных форматов (html, pdf, md, cookies и т.д.), а также захвата формата основного скриншота.

Использует POST API Urlbox.com для продвинутого рендеринга с боковыми рендерами. Скачивание на компьютер через store_renders: true. Идеально подходит для: использования множества опций, конвертации сайтов в HTML/PDF/markdown, извлечения метаданных, сохранения куки, рендеринга кастомного HTML/CSS/JS и одновременной генерации нескольких выходных форматов (html, pdf, md, cookies и т.д.), а также захвата формата основного скриншота.

Параметры

  • store_rendersboolean

    Flip this to true to save all downloadable render links

  • urlstringобязательный

    The URL or domain of the website you want to screenshot.

  • htmlstring

    The HTML you want to render if not a URL.

  • formatenum

    The output format of the resulting render.

    pngjpegwebpavifsvgpdfmp4webmhtmlmhtmljsonmdsvg
  • widthnumber

    The viewport width of the browser, in pixels.

  • heightnumber

    The viewport height of the browser, in pixels.

  • full_pageboolean

    Specify whether to capture the full scrollable area of the website.

  • selectorstring

    Take a screenshot of the element that matches this selector.

  • clipstring

    Clip the screenshot to the bounding box specified by x,y,width,height.

  • gpuboolean

    Enable GPU acceleration to render 3D scenes and heavy WebGL content.

  • block_adsboolean

    Blocks requests from popular advertising networks from loading.

  • hide_cookie_bannersboolean

    Automatically hides cookie banners from most websites.

  • click_acceptboolean

    Attempts to click on the 'Accept' button to accept cookies.

  • press_escapeboolean

    Attempts to press the Escape (ESC) key before capturing the page.

  • block_urlsstring[]

    Block requests from specific domains from loading. You can use wildcard characters to match subdomains.

  • block_imagesboolean

    Blocks image requests

  • block_fontsboolean

    Blocks font requests

  • block_mediasboolean

    Block video and audio requests

  • block_stylesboolean

    Prevent stylesheet requests from loading

  • block_scriptsboolean

    Prevent requests for javascript scripts from loading

  • block_framesboolean

    Block frames.

  • block_fetchboolean

    Block fetch requests from the target URL.

  • block_xhrboolean

    Block XHR requests from the target URL.

  • block_socketsboolean

    Block websocket requests.

  • hide_selectorstring

    Comma-delimited string of CSS element selectors that are hidden.

  • jsstring

    Execute custom JavaScript in the context of the page.

  • cssstring

    Inject custom CSS into the page

  • dark_modeboolean

    Emulate dark mode on websites by setting prefers-color-scheme: dark

  • reduced_motionboolean

    Prefer less animations on websites by setting prefers-reduced-motion: reduced

  • show_timestampboolean

    Shows a timestamp in a header above the rendered screenshot.

  • show_urlboolean

    Shows a URL in a header above the rendered screenshot.

  • retinaboolean

    Take a 'retina' or high-definition screenshot, equivalent to setting a device pixel ratio of 2.0.

  • img_fitenum

    How the screenshot should be resized or cropped to fit the dimensions.

    covercontainfillinsideoutside
  • img_positionenum

    How the image should be positioned when using an img_fit of cover or contain.

    northnortheasteastsoutheastsouthsouthwestwestnorthwestcenter
  • img_bgstring

    Background colour to use when img_fit is contain, or img_pad is used.

  • img_padstring

    Pad the screenshot, giving it a border.

  • qualitynumber

    The image quality of the resulting screenshot (JPEG/WebP only)

  • transparentboolean

    If a website has no background color set, the image will have a transparent background.

  • max_heightnumber

    Limit the screenshot to a maximum height.

  • pdf_page_sizeenum

    Sets the PDF page size.

    A0A1A2A3A4A5A6LegalLetterLedgerTabloid
  • pdf_page_rangestring

    Sets the PDF page range to return.

  • pdf_page_widthnumber

    Sets the PDF page width, in pixels.

  • pdf_page_heightnumber

    Sets the PDF page height, in pixels.

  • pdf_marginstring

    Sets the margin of the PDF document.

  • pdf_outlineboolean

    Generates an outline for the PDF.

  • pdf_taggedboolean

    Generates a tagged PDF.

  • pdf_margin_topstring

    Sets a custom top margin on the PDF.

  • pdf_margin_rightstring

    Sets a custom right margin on the PDF.

  • pdf_margin_bottomstring

    Sets a custom bottom margin on the PDF.

  • pdf_margin_leftstring

    Set a custom left margin on the PDF.

  • pdf_auto_cropboolean

    Automatically remove white space from PDF.

  • pdf_scalenumber

    Sets the scale factor of the website content in the PDF.

  • pdf_orientationenum

    Sets the orientation of the PDF.

    portraitlandscape
  • pdf_backgroundboolean

    Sets whether to print background images in the PDF

  • disable_ligaturesboolean

    Prevents ligatures from being used.

  • mediaenum

    By default, when generating a PDF, the print CSS media query is used.

    screenprint
  • pdf_show_headerboolean

    Whether to show the default pdf header on each page of the pdf.

  • pdf_headerstring

    Change the default pdf header that is shown on each page of the pdf.

  • pdf_show_footerboolean

    Whether to show the default pdf footer on each page of the pdf.

  • pdf_footerstring

    Change the default pdf footer that is shown on each page of the pdf.

  • readableboolean

    Make the pdf into a readable document by removing unnecessary elements.

  • forceboolean

    Generate a fresh render, instead of getting a cached version.

  • uniquestring

    Pass a unique string such as a UUID, hash or timestamp.

  • ttlnumber

    The duration to keep a render in the cache, in seconds.

  • proxystring

    Pass in a proxy server address to make screenshot requests via that server.

  • headerany

    Set a header on the request when loading the URL

  • cookieany

    Sets a cookie on the request when loading the URL.

  • user_agentany

    Sets the User-Agent string for the request

  • platformstring

    Sets the navigator.platform that the browser will report for the request.

  • accept_langstring

    Sets an Accept-Language header on requests to the target URL

  • authorizationstring

    Sets an Authorization header on requests to the target URL.

  • tzstring

    Emulate the timezone to use when rendering pages.

  • engine_versionenum

    Sets the version of the urlbox rendering engine to use. Latest provides the latest bug fixes and features.

    lateststable
  • certifyboolean

    Creates a hash of the rendered file, timestamp and options providing proof.

  • delaynumber

    The amount of time to wait before Urlbox captures a render in milliseconds.

  • timeoutnumber

    The amount of time to wait for the requested URL to load, in milliseconds.

  • wait_untilenum

    Waits until the specified DOM event has fired before capturing a render.

    domloadedmostrequestsfinishedrequestsfinishedloaded
  • wait_forstring

    Waits for the element specified by this selector to be present in the DOM.

  • wait_to_leavestring

    Waits for the element specified by this selector to be absent from the DOM.

  • wait_timeoutnumber

    The amount of time to wait for the wait_for element to appear.

  • fail_if_selector_missingboolean

    Fails the request if the elements specified by selector or wait_for options are not found.

  • fail_if_selector_presentboolean

    Fails the request if the element specified by wait_to_leave option is found.

  • fail_on_4xxboolean

    If true and the requested URL returns a status code between 400 and 499, Urlbox will fail.

  • fail_on_5xxboolean

    If true and the requested URL returns a status code between 500 and 599, Urlbox will fail.

  • scroll_tostringnumber

    Scroll, to either an element or to a pixel offset from the top.

  • clickany

    Specifies an element selector to click before generating a screenshot or PDF

  • click_allany

    Specifies an element selector to click all matching elements.

  • hoverstring

    Specifies an element selector to hover over before generating a screenshot or PDF

  • bg_colorstring

    Specify a hex code or CSS color string to use as the background color

  • full_page_modeenum

    Whether to use scroll and stitch algorithm or native full page screenshot.

    scrollnative
  • full_widthboolean

    When full_page=true, specify whether to capture the full width of the website.

  • allow_infiniteboolean

    Override the default behavior to prevent infinite scrolling.

  • skip_scrollboolean

    Speed up renders by skipping an initial scroll through the page.

  • detect_full_heightboolean

    Prevent backgrounds from getting stretched when making a full page screenshot.

  • max_section_heightnumber

    The maximum height of each image section when taking a full_page screenshot.

  • scroll_incrementnumber

    Sets how many pixels to scroll when scrolling the page.

  • scroll_delaynumber

    The time to wait between taking the screenshots of each individual section.

  • highlightstring

    Specify a string to highlight on the page before capturing a screenshot or PDF.

  • highlightfgstring

    Specify the text color of the highlighted word.

  • highlightbgstring

    Specify the background color of the highlighted word.

  • latitudenumber

    Sets the latitude used to emulate the Geolocation API.

  • longitudenumber

    Sets the longitude used to emulate the Geolocation API.

  • accuracynumber

    Sets the accuracy of the Geolocation API in metres.

  • use_s3boolean

    Save the render directly to the S3 (or S3-Compatible) bucket configured on your account.

  • s3_pathstring

    Sets the S3 path, including subdirectories and the filename.

  • no_suffixboolean

    By default, urlbox adds the file extension to the s3_path.

  • s3_bucketstring

    Overrides the configured bucket to use when saving the render.

  • s3_endpointstring

    Change the endpoint URL to use an S3 compatible storage provider.

  • s3_regionstring

    Override the configured S3 region when saving the render.

  • cdn_hoststring

    If your custom bucket is fronted by a CDN, you can set the host name here.

  • s3_storageclassstring

    Sets the s3 storage class.

  • save_htmlboolean

    Alongside rendering the main options.format shot, also saves the render as HTML returning a storage URL.

  • save_metadataboolean

    Alongside rendering the main options.format shot, also saves render's Metadata returning a storage URL.

  • save_markdownboolean

    Alongside rendering the main options.format shot, also saves render as Markdown returning a storage URL.

  • save_mhtmlboolean

    Alongside rendering the main options.format shot, also saves render as MHTML returning a storage URL.

  • save_cookiesboolean

    Alongside rendering the main options.format shot, also saves renders used cookies returning a storage URL.

  • povstring

    Use a Point of View (PoV) to more convincingly and accurately emulate loading a website from a particular location, with better success than many other options here. This lets you view a website as if you were browsing from a less block-prone perspective, such as through a trusted, location-specific, or residential IP. - hidden - The basic level of anonymisation to mask your location (great starting place) - trusted - Using more trusted, reliable networks to get a higher success rate when emulating a country - stealth - Advanced protocols designed to bypass bot detection - premium - Emulates high-quality residential networks for maximum reliability over hidden and trusted - geo - Location-specific access from real devices in your target country This option is not compatible when trying to use authorization or cookies.

  • pov_countrystring

    You can also specify a particular country for your PoV by adding a country code such as: us, gb, ca - If we don't have one available, do contact support@urlbox.com and we'll see what we can do.

Другие проверенные MCP-сервера

CircleCI/mcp-server-circleci

CircleCI/mcp-server-circleci

официальный

MCP-сервер для интеграции CircleCI с AI-ассистентами: запускайте пайплайны, анализируйте сбои, находите flaky тесты и управляйте CI/CD прямо из IDE через естественный язык. Полезен командам, ускоря...

TypeScript86
anaisbetts/mcp-installer

anaisbetts/mcp-installer

MCP сервер, который автоматически устанавливает другие MCP серверы из npm и PyPi по запросу. Помогает разработчикам и пользователям Claude быстро добавлять нужные инструменты через простые команды. Требует npx и uv.

JavaScript1532
QuantConnect/mcp-server

QuantConnect/mcp-server

официальный

Официальный MCP сервер QuantConnect — мост между AI-ассистентами и платформой. Через API позволяет создавать проекты, писать стратегии, запускать бэктесты и управлять live-трейдингом. Удобен для ра...

Python78
browserbase/mcp-server-browserbase

browserbase/mcp-server-browserbase

официальный

MCP сервер облачной автоматизации браузера Browserbase. Позволяет AI-агентам навигировать по сайтам, извлекать данные и выполнять действия. Полезен для RPA и веб-скрапинга. Доступен self-hosted и hosted.

TypeScript3408
InfluxData/influxdb3_mcp_server

InfluxData/influxdb3_mcp_server

официальный

MCP сервер для InfluxDB 3: SQL-запросы, запись line protocol, управление базами и токенами. Более 20 инструментов для Core, Enterprise, Cloud. Незаменим для инженеров данных и DevOps, работающих с ...

TypeScript36
Doist/todoist-mcp

Doist/todoist-mcp

официальный

MCP сервер для Todoist даёт AI-агентам полный доступ к задачам. Создавайте, ищите и редактируйте задачи через LLM. Поддерживает streamable HTTP, OAuth, интеграцию с Claude, Cursor и VS Code. Инструменты переиспользуемы и работают как MCP, так и напрямую.

TypeScript528
© Каталог MCP, 2026. Все права защищены.
Проект не аффилирован с Anthropic и любыми упомянутыми продуктами.
Все названия и торговые марки принадлежат их владельцам.
Контакты для связи: hi@mcp-katalog.ru

Лука Никитин