Stitch MCP
A universal MCP server for Google Stitch that enables AI-powered UI/UX design generation by extracting design context and metadata from existing screens. It allows users to fetch screen code and images to create consistent, styled UI components across multiple projects.
README
Stitch MCP
<div align="center">
Universal MCP Server for Google Stitch
</div>
Build amazing UI/UX designs instantly with AI. Works seamlessly with Cursor, Claude, Antigravity, and any MCP-compatible editor.
Created by Aakash Kargathara.
🚀 How It Works
✨ Why this is cool
- Zero Config: Just login once and it works everywhere.
- Universal: Works on Windows, Mac, and Linux.
- Free: Google Stitch API is free to use.
�️ Quick Setup (2 Minutes)
1. Prerequisite: Google Cloud
You need a Google Cloud project with the Stitch API enabled.
# Login to your Google Cloud
gcloud auth login
# Set your project (replace with your actual project ID)
gcloud config set project YOUR_PROJECT_ID
gcloud auth application-default set-quota-project YOUR_PROJECT_ID
# Enable the magic
gcloud beta services mcp enable stitch.googleapis.com
2. Install the Credentials
This gives stitch-mcp permission to talk to Google on your behalf.
gcloud auth application-default login
3. Add to Your AI Editor
Copy and paste this into your MCP config file:
For Claude Desktop:
~/Library/Application Support/Claude/claude_desktop_config.json
For Cursor: Settings > MCP > Add New Server
{
"mcpServers": {
"stitch": {
"command": "npx",
"args": ["-y", "stitch-mcp"],
"env": {
"GOOGLE_CLOUD_PROJECT": "YOUR_PROJECT_ID"
}
}
}
}
🛠️ Available Tools
| Tool Name | What it does |
|---|---|
extract_design_context |
🧠 Scans a screen to extract "Design DNA" (Fonts, Colors, Layouts). Use this to keep style consistent. |
fetch_screen_code |
💾 Downloads the raw HTML/Frontend code of a screen. |
fetch_screen_image |
🖼️ Downloads the high-res screenshot of a screen. |
generate_screen_from_text |
✨ Generates a NEW screen based on your prompt (and context). |
create_project |
📁 Creates a new workspace/project folder. |
list_projects |
📋 Lists all your available Stitch projects. |
list_screens |
📱 Lists all screens within a specific project. |
get_project |
🔍 Retrieves details of a specific project. |
get_screen |
ℹ️ Gets metadata for a specific screen. |
💡 Pro Tip: The "Designer Flow"
To generate consistent UI, use this 2-step flow:
- Extract: "Get design context from the Home Screen..."
- Generate: "Using that context, generate a Chat Screen..."
This ensures your new screen matches your existing design system perfectly.
📄 License
Apache 2.0 - Open source and free to use.
Star History
Built with ❤️ by Aakash Kargathara
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。