MCP-сервер Screenrove

• Имя в реестреcom.screenrove/screenroveподтверждён в реестре MCP

Имя в реестре лежит в пространстве screenrove.com. Реестр пускает в такое пространство только того, кто доказал владение доменом через DNS или HTTP.

• Состояниеотвечаетпроверено 2026-10-25
• Инструменты22
• Сервер называет себяscreenrove
• Версия сервера1.5.0
• Версия протокола2025-06-18

2026-10-25 сервер ответил на initialize и tools/list без входа. Первый ответ за 2051 мс.

• Инструменты делают все проверенные сценарии: Study real product screens and user flows for reference; Pull design references into a coding agent through MCP; Compare sign-up and onboarding flows across many products.
• Проверок пока 3 из 7, нужных, чтобы судить о надёжности.

Вывод сделан правилами по замерам выше. Вероятный первый вызов выбрала модель по списку инструментов: прочитайте описание, прежде чем на него полагаться.

• Оценка INITE MCPчерез неделюдля оценки нужно 7 ежедневных проверок, пока 3
• Что агент может с ним сделать3 из 3 сценариев
• Отвечалидёт замерпроверок пока 3, долю покажем после 7
• Медиана первого ответа2682 мс
• Место в контексте агента≈ 6 782 токеновописания всех инструментов (22), они занимают контекст агента на каждом ходу
• Описания инструментовA · 100 из 100
• Типизированные ответы21 из 22 инструментовобъявлен outputSchema: ответ приходит с типами и читается сразу

• Все инструменты проходят все шесть проверок.

Программа проверяет сервер раз в день: initialize и tools/list, без модели. Токены - это длина описаний из расчёта примерно четыре символа на токен. Оценка - среднее шести проверок имени, описания, схемы и аннотаций каждого инструмента. Она говорит, насколько понятно описаны инструменты, а не о том, работают ли они. Оценка складывается только из замеренного: отвечает ли сервер (25%), делает ли работу продукта (25%), описания (20%), контекст (10%), использование (10%) и насколько просто подключиться (10%). Незамеренная часть не учитывается, а скрытая инструкция ограничивает оценку 40 баллами. Состояние MCP-серверов вендоров: методика и цифры →

• build_handoff

  Generate a complete build prompt for a coding agent: ordered screens with notes, observed transitions, links to up to 10 agent-sized images (1x copies and page-section crops, never taller than 8000px, each with its pixel size), the…

• build_recipe

  Combine specific screens from different products, plus one visual style, into a single build brief. Each screen contributes one thing (say what with "id: what to take"); structure comes from the screens and every visual token comes from…

• check_my_ui

  Compare the user's UI structure against Screenrove's catalog of real products. Describe what the user has (screen type, sections, flow steps, plan count) and get a report showing the closest real-world references with factual comparisons…

• compare_screens

  Compare two captured screens side by side: layout structure, page sections, observed actions, dimensions, screen types, and design guide differences. Returns a structured comparison with similarities, differences, and factual…

• find_related_screens

  Find screens from other products that solve the same design problem as this one: same primary pattern first, then shared tasks, states and components (rarer tags count more). At most two per product. Each result says why it matched. Use…

• get_design

  Get the measured design guide for a product: observed font families, color palette, type scale, layout patterns, spacing values, and component observations. Marketing site and product UI are measured separately. Use this when you want to…

• get_flow

  Get the complete onboarding flow for a product: every step in order with titles, notes on what happens, observed transitions (button labels and where they lead), and which steps are alternate branches. Includes the handoff reference id to…

• get_motion

  Get one motion entry as a build prompt: what moves and how (every property, duration, easing curve or spring, delay and trigger), why it feels good, what a rebuild must keep, Screenrove's working vanilla HTML/CSS/JS implementation, and…

• get_motion_guidelines

  Get house rules for UI motion (durations, which easing for enter and exit, springs, what to animate, reduced motion) with citations, plus ready-to-use duration and easing tokens, the motion library's sources and its category and trigger…

• get_product

  Get a product's full collection: coverage notes, design summary, and every captured screen grouped into onboarding flow, marketing pages, and in-product screens. Use this to explore a competitor's complete UI: their signup flow, pricing…

• get_screen

  Get everything recorded about one screen: notes on what it does and how it's laid out, source URL, image URLs and dimensions, observed actions and where they lead, and page sections for long marketing pages. Use this to understand a…

• get_screen_image

  Get the actual screenshot so you can see the UI. For marketing pages taller than 4000px, preview returns only the first screen (above the fold); use size=full for the whole page, which can exceed what vision models accept. getScreen lists…

• list_flows

  List every captured user journey: onboarding flows, signup sequences, checkout processes, booking flows, and marketplace explorations. Shows step counts, flow type, and observed transitions between steps. Use this to find complete user…

• list_products

  List every product in the UI reference catalog with its capture date, tags, coverage notes and screen counts. Start here to see what competitor products, design systems, and UI patterns are available. Products include: Linear, Cursor…

• list_tags

  List the tag vocabulary for searching by design problem: four facets (task, pattern, component, state), each tag with its definition, aliases and how many screens carry it. Use the ids with searchScreens or pickReference, e.g…

• name_patterns

  Summarise how real products are named: each naming pattern with its share and examples, the commonest TLDs, domain styles, length and syllable distributions, and a per-category table (top TLD, share on .ai, share on the exact .com, top…

• pick_reference

  Show the user several matching UI references side by side in their browser and let them click the one to build from. Returns a URL to open for them. Prefer this over sending full-page images whenever the user should decide which reference…

• search_logos

  Search the logos of the products in Screenrove's library, as references for designing a logo or app icon. Each logo is the product's own mark as its site serves it (SVG icon, apple-touch-icon or large favicon; never redrawn), linked to…

• search_motion

  Search the motion library: polished UI animations and micro-interactions (button presses, toggles, toasts, number tickers, thinking states, hover effects, interaction sounds) curated from open-source component libraries and designers'…

• search_names

  Search about 700 real product names - Screenrove's library plus a curated list of products on Mobbin and Refero - each with its domain and TLD, category and derived traits: naming pattern (real-word, compound, blend, altered, suffix…

• search_screens

  Search the UI reference catalog by design problem and keyword. Every screen is tagged on four facets: task (what the person is doing), pattern (screen archetype), component (building blocks) and state (empty, filtered, error...). Filter…

• wait_for_pick

  Wait for the user to choose on the pick page. Long-polls up to 50 seconds—returns as soon as they click, or status "pending" after the wait (call again if so). Once chosen, returns their reference with its screenshot and a full build…