Fragen Sie Claude Code (oder einen beliebigen MCP-Client):
Entwirf das Home-Dashboard für einen Fitness-Tracker. Drei konzentrische Aktivitätsringe, wöchentliches Balkendiagramm, Liste der letzten Workouts, Premium-Dark-Mode mit Neon-Akzenten.
mockit-mcp liefert ein echtes PNG-Mockup (Größe 390×844 bei 2x Skalierung, ein Viewport der iPhone-Klasse) und den zugrunde liegenden HTML/Tailwind-Quellcode – damit Sie visuell iterieren und auf SwiftUI portieren können, wenn Sie bereit für die Entwicklung sind.
Es ist keine statische Template-Engine und kein generischer KI-Müll. Der System-Prompt ist handoptimiert für erstklassige iOS-Ästhetik: echte Inhalte, SVG-Icons (keine Emojis), geschmackvolle Verläufe anstelle von Stockfotos, iOS HIG-Typografie-Skalierung und tonale Schichtung anstelle von schweren Schatten.
Related MCP server: Playwright MCP for macOS
Zwei Backends, dieselben Tools. Nutzen Sie das lokale claude CLI (Abonnement, keine Extrakosten) oder die Anthropic-API (Key + nutzungsbasierte Abrechnung). Wechseln Sie mit einer Umgebungsvariablen.
Echte PNG-Ausgabe. Headless Chromium via Playwright. Standard-Viewport ist 390×844 @2x (iPhone-Klasse); jede benutzerdefinierte Größe ist nur eine Umgebungsvariable entfernt.
Iterative Verfeinerung. iterate_screen nimmt eine Screen-ID + Feedback ("mach die Hero-Card kleiner") und erstellt eine neue Version, wobei Eltern-/Kind-Beziehungen nachverfolgt werden.
Festplattenbasierte Bibliothek. Jede Generierung speichert HTML + PNG + JSON-Metadaten. Durchsuchen, filtern, erneut exportieren.
MCP-Standard. Funktioniert mit Claude Code, Claude Desktop, Cursor, Windsurf oder jedem MCP-Client.
Stdio + HTTP-Transporte. Lokal für die Entwicklung ausführen oder als Netzwerkdienst für geteilte/containerisierte Nutzung.
Tool | Beschreibung |
| Text-Briefing → PNG + HTML. Optionale |
| Nimmt eine vorherige |
| Listet Screens auf, optional gefiltert nach Projekt. |
| Ruft Metadaten (oder vollständiges HTML) für einen bestimmten Screen ab. |
Node.js 20+
Entweder das angemeldete claude CLI (cli-Backend, Standard) oder einen Anthropic-API-Key (api-Backend)
Playwrights Chromium-Download (~170 MB, einmalig)
git clone https://github.com/karyaboyraz/mockit-mcp.git
cd mockit-mcp
npm install
npx playwright install chromium
npm run buildZu Claude Code hinzufügen:
claude mcp add mockit -- node "$(pwd)/dist/server.js"Fertig. Kein API-Key erforderlich – es nutzt Ihre bestehende claude CLI-Sitzung.
claude CLI auf dem Host)echo "CLAUDE_BACKEND=api" > .env
echo "ANTHROPIC_API_KEY=sk-ant-..." >> .env
npm run build
claude mcp add mockit -- node "$(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 --buildStandardmäßig bindet docker-compose.yml den HTTP-Port nur an 127.0.0.1 und der Server erfordert MCP_HTTP_TOKEN für jede Anfrage, die nicht vom Loopback kommt. Setzen Sie diesen Server keinem öffentlichen Netzwerk aus, ohne ein starkes MCP_HTTP_TOKEN zu konfigurieren – jede Generierung belastet Ihren Anthropic-API-Key.
Verweisen Sie dann jeden Client auf die Loopback-URL:
claude mcp add --transport http mockit http://127.0.0.1:7821/mcp \
-H "Authorization: Bearer <MCP_HTTP_TOKEN>"Für Fernzugriff ändern Sie das Port-Binding in der docker-compose.yml auf 0.0.0.0:7821:7821 und stellen Sie sicher, dass MCP_HTTP_TOKEN gesetzt ist – andernfalls verweigert der Server den Start.
Fragen Sie in einem beliebigen MCP-Client einfach:
Entwirf ein Fitness-Tracker-Dashboard. Zeige den heutigen Ring-Fortschritt, ein wöchentliches Diagramm und eine Liste der letzten Workouts. Dark Mode, neon-grüner Akzent.
Das PNG erscheint inline. Das HTML wird unter designs/{project}/{name}-{id}.html gespeichert.
Für Nachbesserungen:
iterate_screen auf diesem Fitness-Dashboard — ersetze das Diagramm durch die Herzfrequenz über die Zeit und füge einen "Workout teilen"-Button darunter hinzu.
Siehe examples/ für Prompt-Muster und vollständige Ausgaben.
Alles optional. Siehe .env.example für die vollständige Liste.
Env | Standard | Notizen |
|
|
|
| — | Nur für |
|
| Nur API-Backend. Wenn Ihr Konto keinen Opus-Zugriff hat, setzen Sie es auf |
|
| Pfad zum |
|
| Subprocess-Timeout |
|
|
|
|
| HTTP-Transport-Port |
|
| Bind-Interface; Nicht-Loopback erfordert |
| — | Bearer-Token für HTTP-Auth. Erforderlich, wenn |
|
| Wo Ausgaben gespeichert werden |
|
| Render-Breite in CSS-Pixeln |
|
| Render-Höhe in CSS-Pixeln |
|
| Retina-Faktor (finales PNG ist |
|
|
|
Pro Generierung: ~3K Input-Token (System-Prompt) + ~6–12K Output-Token, abhängig von der Screen-Komplexität. Die Ausgabe dominiert die Kosten bei Opus.
Backend | Erster Aufruf | Zwischengespeicherte Nachbesserung |
| zählt gegen Ihr Claude Code-Abonnement-Kontingent | gleich — Cache rabattiert nur den System-Prompt |
| ~$0.50–0.95 (Opus 4.7) | ~$0.45–0.90 (Cache rabattiert nur den System-Prompt-Input; Output-Kosten bleiben unverändert) |
System-Prompt-Caching ist standardmäßig aktiviert (5 Minuten TTL). Es spart ein paar Cent pro Aufruf, ist aber kein Rabatt in der Größenordnung von Zehnerpotenzen – Output-Token werden weiterhin zum vollen Preis berechnet. Für echte Kostenreduzierung wechseln Sie zu einem kleineren Modell (claude-sonnet-4-6 oder 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, costDer handoptimierte System-Prompt befindet sich in src/system-prompt.ts. Hier sind die Durchsetzung der iOS HIG, die Regel gegen Stockfotos, die SF Pro-Fallback-Kette und die redaktionellen Typografie-Präferenzen kodiert. Wollen Sie stattdessen Material You oder eine Desktop-Dashboard-Stimme? Bearbeiten Sie ihn.
npm run dev # tsx watch mode, stdio transport
npm run http # tsx watch mode, http transport on :7821
npm run build # compile to dist/[ ] Watch / iPad / Android Viewport-Presets
[ ] Multi-Screen-Flow-Generierung (Onboarding-Sequenzen)
[ ] HTML → SwiftUI / Jetpack Compose Port-Tool
[ ] Design-System-Import (Tailwind-Konfiguration, Design-Tokens)
[ ] Bildreferenzen (nutzen Sie --image für visuelle Inspiration)
[ ] Varianten-Generierung (3-5 Alternativen pro Prompt)
Issues und PRs sind willkommen – siehe CONTRIBUTING.md.
Aufgebaut auf:
Anthropic Claude — das Modell, das die schwere Arbeit leistet
Model Context Protocol — der Integrationsstandard
Playwright — der Renderer
Tailwind CSS — via CDN, in jedem generierten Screen
iPhone, iPad, Apple Watch und iOS sind Marken von Apple Inc. Claude ist eine Marke von Anthropic, PBC. mockit-mcp ist ein unabhängiges Open-Source-Projekt und ist nicht mit Apple Inc. oder Anthropic, PBC verbunden, wird von diesen nicht unterstützt oder gesponsert. Alle anderen Produktnamen, Logos und Marken sind Eigentum ihrer jeweiligen Inhaber.
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.
