Спросите Claude Code (или любого MCP-клиента):
Разработай домашний дашборд для фитнес-трекера. Три концентрических кольца активности, еженедельная гистограмма, список недавних тренировок, премиальная темная тема с неоновыми акцентами.
mockit-mcp возвращает настоящий PNG-макет (размером 390×844 при масштабе устройства 2x, вьюпорт класса iPhone) и исходный код HTML/Tailwind — чтобы вы могли визуально итерировать и перенести его в SwiftUI, когда будете готовы к разработке.
Это не статический движок шаблонов и не низкокачественная ИИ-поделка. Системный промпт вручную настроен на премиальную эстетику iOS: реальный контент, SVG-иконки (без эмодзи), стильные градиенты вместо стоковых фото, типографика по HIG (Human Interface Guidelines) и тональная многослойность вместо тяжелых теней.
Related MCP server: Playwright MCP for macOS
Два бэкенда, одни и те же инструменты. Используйте локальный CLI claude (подписка, без доплат) или API Anthropic (ключ + оплата за вызов). Переключайтесь одной переменной окружения.
Реальный вывод в PNG. Безголовый Chromium через Playwright. Вьюпорт по умолчанию — 390×844 @2x (класс iPhone); любой пользовательский размер задается одной переменной окружения.
Итеративное уточнение. iterate_screen принимает ID экрана + обратную связь ("сделай карточку героя меньше") и создает новую версию, отслеживая связь родитель/потомок.
Библиотека на диске. Каждая генерация сохраняет HTML + PNG + JSON-метаданные. Просматривайте, фильтруйте, экспортируйте повторно.
Стандарт MCP. Работает с Claude Code, Claude Desktop, Cursor, Windsurf или любым другим MCP-клиентом.
Транспорты Stdio + HTTP. Запускайте локально для разработки или как сетевой сервис для общего/контейнеризированного использования.
Инструмент | Описание |
| Текстовое задание → PNG + HTML. Опциональные поля |
| Берет предыдущий |
| Список экранов, опционально с фильтрацией по проекту. |
| Получить метаданные (или полный HTML) для конкретного экрана. |
Node.js 20+
Либо авторизованный CLI claude (cli бэкенд, по умолчанию), либо API-ключ Anthropic (api бэкенд)
Загрузка Chromium для Playwright (~170 МБ, единоразово)
git clone https://github.com/karyaboyraz/mockit-mcp.git
cd mockit-mcp
npm install
npx playwright install chromium
npm run buildДобавьте в Claude Code:
claude mcp add mockit -- node "$(pwd)/dist/server.js"Готово. API-ключ не нужен — используется ваша существующая сессия CLI claude.
claude)echo "CLAUDE_BACKEND=api" > .env
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env
npm run build
claude mcp add mockit -- node "$(pwd)/dist/server.js"cat > .env <<'ENV'
CLAUDE_BACKEND=api
ANTHROPIC_API_KEY=sk-ant-...
# Required if you change the port binding from 127.0.0.1 to 0.0.0.0:
MCP_HTTP_TOKEN=$(openssl rand -hex 32)
ENV
docker compose up -d --buildПо умолчанию docker-compose.yml привязывает HTTP-порт только к 127.0.0.1, и сервер требует MCP_HTTP_TOKEN для любого запроса не с локальной машины. Не открывайте этот сервер в публичную сеть без установки надежного MCP_HTTP_TOKEN — каждая генерация расходует лимиты вашего API-ключа Anthropic.
Затем укажите любому клиенту URL локальной петли:
claude mcp add --transport http mockit http://127.0.0.1:7821/mcp \
-H "Authorization: Bearer <MCP_HTTP_TOKEN>"Для удаленного доступа измените привязку порта в docker-compose.yml на 0.0.0.0:7821:7821 и убедитесь, что установлен MCP_HTTP_TOKEN — в противном случае сервер откажется запускаться.
В любом MCP-клиенте просто спросите:
Разработай дашборд фитнес-трекера. Покажи прогресс колец за сегодня, еженедельную диаграмму и список недавних тренировок. Темная тема, неоново-зеленый акцент.
PNG появится в чате. HTML будет сохранен в designs/{project}/{name}-{id}.html.
Для последующих правок:
iterate_screen для того фитнес-дашборда — замени диаграмму на пульс во времени и добавь кнопку "поделиться тренировкой" внизу.
См. examples/ для примеров промптов и готовых результатов.
Все опционально. См. .env.example для полного списка.
Переменная | По умолчанию | Примечания |
|
|
|
| — | Требуется только для |
|
| Только для API бэкенда. Если у вашего аккаунта нет доступа к Opus, установите |
|
| Путь к бинарному файлу |
|
| Таймаут подпроцесса |
|
|
|
|
| Порт HTTP транспорта |
|
| Интерфейс привязки; для внешних запросов требуется |
| — | Bearer-токен для HTTP-авторизации. Обязателен, если |
|
| Где сохраняются результаты |
|
| Ширина рендера в CSS-пикселях |
|
| Высота рендера в CSS-пикселях |
|
| Коэффициент Retina (итоговый PNG будет шириной |
|
|
|
За одну генерацию: ~3 тыс. входных токенов (системный промпт) + ~6–12 тыс. выходных токенов в зависимости от сложности экрана. Выходные токены составляют основную часть стоимости на Opus.
Бэкенд | Первый вызов | Итерация с кэшем |
| учитывается в квоте подписки Claude Code | то же самое — кэш дает скидку только на системный промпт |
| ~$0.50–0.95 (Opus 4.7) | ~$0.45–0.90 (кэш дает скидку только на входной системный промпт; стоимость вывода не меняется) |
Кэширование системного промпта включено по умолчанию (TTL 5 минут). Это экономит несколько центов за вызов, но не является скидкой на порядок — выходные токены все равно оплачиваются по полной ставке. Для реального снижения затрат переключитесь на модель поменьше (claude-sonnet-4-6 или claude-haiku-4-5).
┌─────────────────┐
│ MCP Client │ (Claude Code, Cursor, Windsurf, …)
└────────┬────────┘
│ tool call: generate_screen({ prompt, ... })
▼
┌─────────────────────────────────────────────────────┐
│ mockit-mcp │
│ │
│ ┌──────────────┐ ┌────────────────────────┐ │
│ │ Backend │ │ Renderer │ │
│ │ │ │ │ │
│ │ ► cli ─────┼──► │ Playwright (headless │ │
│ │ ► api ─────┘ │ Chromium @ iPhone │ │
│ │ → HTML+Tailwind │ viewport) │ │
│ └──────────────┘ │ → PNG screenshot │ │
│ └────────────────────────┘ │
│ │
│ ┌────────────────────────────────────────────┐ │
│ │ Storage (disk): HTML + PNG + JSON metadata │ │
│ └────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────┘designs/
└── {project-slug}/
├── {name-slug}-{id8}.html # id8 = first 8 chars of the screen UUID
├── {name-slug}-{id8}.png
└── {name-slug}-{id8}.json # full UUID, prompt, parent ID, tokens, model, costВручную настроенный системный промпт находится в src/system-prompt.ts. Именно там закодированы соблюдение iOS HIG, правило отсутствия стоковых фото, цепочка фоллбэков SF Pro и предпочтения в типографике. Хотите Material You или стиль десктопного дашборда? Отредактируйте его.
npm run dev # tsx watch mode, stdio transport
npm run http # tsx watch mode, http transport on :7821
npm run build # compile to dist/[ ] Пресеты вьюпортов для Watch / iPad / Android
[ ] Генерация потоков из нескольких экранов (последовательности онбординга)
[ ] Инструмент переноса HTML → SwiftUI / Jetpack Compose
[ ] Импорт дизайн-системы (конфиг Tailwind, дизайн-токены)
[ ] Ссылки на изображения (используйте --image для визуального вдохновения)
[ ] Генерация вариантов (3-5 альтернатив на промпт)
Проблемы и PR приветствуются — см. CONTRIBUTING.md.
Построено на базе:
Anthropic Claude — модель, которая выполняет основную работу
Model Context Protocol — стандарт интеграции
Playwright — рендерер
Tailwind CSS — через CDN, в каждом сгенерированном экране
iPhone, iPad, Apple Watch и iOS являются товарными знаками Apple Inc. Claude является товарным знаком Anthropic, PBC. mockit-mcp — это независимый open-source проект, который не связан, не одобрен и не спонсируется Apple Inc. или Anthropic, PBC. Все остальные названия продуктов, логотипы и бренды являются собственностью их соответствующих владельцев.
Generate a premium iOS mobile UI mockup from a text brief. Outputs both the screenshot (PNG) and the underlying HTML. Use this when the user asks to design, mock up, or visualize a mobile app screen.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Detailed brief for the screen: what app, what screen, what content, what UI elements. | |
| project | No | Project name (used to group related screens). | default |
| name | Yes | Short name for this screen, e.g. 'Main', 'Settings', 'Onboarding'. | |
| design_system | No | Optional design system spec: colors, fonts, voice. If omitted, the system invents one consistent with the prompt. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool outputs both a screenshot (PNG) and HTML, which is a key behavioral trait. However, it does not cover other aspects like potential costs, authentication needs, rate limits, or side effects. This is moderate transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loaded with the core functionality in the first sentence and usage guidance in the second. Every word earns its place; no fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters, no output schema, and no annotations, the description provides sufficient context for basic usage: what it generates and when to use it. It could be improved by mentioning the response format or error handling, but for a generation tool with clear output, it is fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for its 4 parameters. The description adds minimal extra meaning beyond the schema, except for the context of 'premium iOS mobile UI mockup' which gives design direction. Baseline 3 is appropriate as schema does heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates a premium iOS mobile UI mockup from a text brief, with both screenshot and HTML output. It distinguishes itself from siblings (get_screen, iterate_screen, list_screens) by focusing on creation rather than retrieval or iteration.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this when the user asks to design, mock up, or visualize a mobile app screen.' This provides clear context for when to use, though it does not explicitly list when not to use or mention alternatives. However, the context of sibling tools implies those alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get details and metadata for a specific screen. Set include_html=true to also return the HTML source.
| Name | Required | Description | Default |
|---|---|---|---|
| screen_id | Yes | Screen UUID returned by generate_screen or iterate_screen. | |
| include_html | No | Include full HTML in response (large). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It mentions the optional HTML return but does not disclose potential size impacts, pagination, or any side effects. Minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that directly state the tool's purpose and key parameter option. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, so 'details and metadata' is vague. While the tool is simple, an agent might benefit from knowing what fields are returned. Adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds minimal extra meaning beyond what the schema already states. For screen_id, it repeats the schema; for include_html, it rephrases slightly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it 'get details and metadata for a specific screen,' which distinguishes it from siblings like generate_screen (create) and list_screens (list all).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this versus alternatives, though sibling names imply the correct use case. The description does provide context for an optional parameter (include_html).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Refine an existing generated screen based on feedback. Use this for follow-up edits like 'change color', 'add a section', 'make it more spacious'.
| Name | Required | Description | Default |
|---|---|---|---|
| screen_id | Yes | ID of the screen to iterate on (from generate_screen output). | |
| feedback | Yes | What to change: 'make the hero card larger', 'use orange accent instead of blue', etc. | |
| name | No | Optional new name for the iteration. Defaults to original name + ' (v2)'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It implies mutation ("refine") but does not specify whether changes are reversible, what permissions are needed, or how the tool handles multiple iterations. The examples are non-destructive, but explicit security or side-effect info is missing.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary action, and includes practical examples without extraneous text. Every sentence adds value and the structure is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description adequately explains the tool's purpose and gives usage examples. However, it does not describe the return value (e.g., updated screen object) or confirm that screen_id must come from generate_screen, which is noted only in the schema. A bit more context on how to use the result would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage, so baseline is 3. The description adds minimal extra meaning beyond the schema's parameter descriptions (e.g., "feedback" examples). The optional "name" parameter is described in both, but the description reinforces but does not significantly augment the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool refines an existing generated screen based on feedback, distinguishing it from siblings like generate_screen (creation) and get_screen (retrieval). The examples of feedback ("change color", "add a section") further clarify its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description specifies that this tool is for follow-up edits after generation, providing clear usage context. However, it does not explicitly state when not to use it (e.g., for new screens or non-generated screens) or mention prerequisites like valid screen_id from generate_screen.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all generated screens, optionally filtered by project name.
| Name | Required | Description | Default |
|---|---|---|---|
| project | No | Filter by project. Omit to list all. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only operation without side effects, which is transparent for a list tool. No annotations exist, but the description is clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that efficiently conveys the tool's purpose and optional parameter without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with one optional parameter and no output schema, the description is adequate. It could be more complete by mentioning the return format, but it still provides sufficient context for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description of the 'project' parameter. The tool description adds 'optionally filtered by project name' but does not add significant new meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('list') and resource ('generated screens') with an optional filter. It distinguishes from siblings like generate_screen and get_screen.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use (listing all screens) and mentions optional filtering, but does not explicitly state when not to use or compare to alternatives like iterate_screen.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1generate_screenget_screeniterate_screenlist_screensScored across 4 tools
Each tool serves a distinct purpose: generate creates, get retrieves, iterate refines, list enumerates. No functional overlap.
All tools follow a consistent verb_noun pattern in snake_case (generate_screen, get_screen, iterate_screen, list_screens).
4 tools is well-scoped for a mockup generation service, covering creation, retrieval, iteration, and listing without excess.
Covers core CRUD except delete, which may be intentional. Users can create, read, update, and list screens, with no obvious dead ends.
Create 3D device mockups, App Store screenshot sets and launch videos from your AI. Showoff.dev puts your screenshots on real iPhones, Pixels, iPads and MacBooks, sets camera and background, and exports App Store and Google Play sizes. Works with Claude, ChatGPT, Cursor, Codex and any MCP client.
Create 3D device mockups, App Store screenshot sets and launch videos from your AI. Showoff.dev puts your screenshots on real iPhones, Pixels, iPads and MacBooks, sets camera and background, and exports App Store and Google Play sizes. Works with Claude, ChatGPT, Cursor, Codex and any MCP client.
Build and edit app screen mockups and clickable prototypes from your AI assistant.
Drive real devices from your AI Coding tool. Embed a client SDK (Unity, Godot, Flutter, iOS/macOS, Android, React Native, Web) in your app, then capture screenshots, traverse the UI tree, inject taps and key events, and run automated test tasks on the physical device over a secure relay.
