mcp-ux-vision
Enables AI-powered visual analysis of webpages for UI/UX assessment, including screenshot capture, element detection, accessibility auditing, and comprehensive JSON reporting.
README
MCP UX Vision
An MCP server that provides AI-powered visual analysis for UI/UX assessment using Google's Gemini Vision API.
Features
- Screenshot capture from URLs
- AI-powered UI element detection and analysis
- WCAG contrast ratio analysis
- Color palette and typography extraction
- Visual accessibility auditing
- Comprehensive JSON reporting
Installation
git clone <repository-url>
cd mcp-ux-vision
npm install
npm run build
Configuration
Add to your MCP client configuration:
{
"servers": {
"ux-vision": {
"command": "node",
"args": [
"path/to/mcp-ux-vision/build/index.js"
]
}
}
}
Tools
screenshot_url
Capture a screenshot of any webpage.
url(required): URL to screenshotfullPage(optional): Capture full page vs viewportwaitTime(optional): Delay before capture (ms)
analyze_screen
Analyze the most recent screenshot with AI, extracting:
- UI elements with geometry and styling
- Color palette and typography
- Accessibility metrics
- Visual hierarchy assessment
generate_report
Create a comprehensive JSON report from the last analysis.
testUrl(required): URL that was analyzedappName(optional): Application nameoutput_path(optional): Report output directory
analyze_url_full_report
One-step workflow combines all above tools with the same parameters: screenshot → analyze → report.
Usage
Once the server is running and configured in your MCP client (like Claude), you can use natural language prompts to call the tools:
screenshot_url
- "Take a screenshot of https://example.com"
- "Capture a full page screenshot of localhost:3000"
- "Screenshot https://myapp.com and wait for the .loading element to disappear"
analyze_screen
- "Analyze the current screenshot for UI elements"
- "Examine the accessibility of this interface"
- "What UI components do you see in the screenshot?"
generate_report
- "Create a UX report for the analysis of https://example.com"
- "Generate a comprehensive UI audit report"
analyze_url_full_report
- "Take a screenshot of https://example.com and create a full UX analysis report"
- "Analyze https://myapp.com and generate a complete accessibility audit"
License
MIT
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。