Frontend Review MCP
An MCP server that reviews UI edit requests by comparing before and after screenshots, providing visual feedback on whether changes satisfy the user's requirements.
Tools
reviewEdit
Perform a visual review of a UI edit request. The 'before screenshot' is a screenshot of the page before the edit, and the 'after screenshot' is the screenshot of the page after the edit. You will recieve either a yes or no response, indicating whether the edit visually satisfies the edit request. If no, it will provide a detailed explanation of why the edit does not satisfy the request so you can continue to work on it.
README
frontend-review-mcp
An MCP server that performs a visual review of a UI edit request. Ask your agent to screenshot the page before and after the edit, and then call this tool to review the edit.
Usage
Cursor
- To install in a project, add the MCP server to your
.cursor/mcp.json:
{
"mcpServers": {
"frontend-review": {
"command": "npx",
"args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"],
}
}
}
- To install globally, add this command to your Cursor settings:
npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key>
Windsurf
- Add the MCP server to your
~/.codeium/windsurf/mcp_config.jsonfile:
{
"mcpServers": {
"frontend-review": {
"command": "npx",
"args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"]
}
}
}
Tools
Currently, the only tool is reviewEdit.
Your Agent will call this tool with the following arguments:
beforeScreenshotPath: The absolute path to the screenshot of the page before the edit.afterScreenshotPath: The absolute path to the screenshot of the page after the edit.editRequest: A detailed description of the UI edit request made by the user.
The tool will return a response with either a yes or no response, indicating whether the edit visually satisfies the edit request. If no, it will provide a detailed explanation of why the edit does not satisfy the request so you can continue to work on it.
Review Model
Currently, the review model is Qwen/Qwen2-VL-72B-Instruct from Hyperbolic. It will automatically retry the request with these models if it fails:
Fallback order:
Qwen/Qwen2-VL-72B-InstructQwen/Qwen2-VL-7B-Instructmeta-llama/Llama-3.2-90B-Vision-Instructmistralai/Pixtral-12B-2409
If you want to use a different model as the first model, you can add the MODEL arg to the command:
npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key> MODEL=<your-model>
It will try the specified model first, and then try the others if it fails.
Taking Screenshots
You can use any MCP server to take screenshots.
AI Instructions
You can include the following instructions in your AI's prompt to make it take screenshots and review the edit:
When making frontend edits:
- Before making any changes, call the mcp_takeScreenshot function to save the current state of the page.
- After making your change, call the mcp_takeScreenshot function again to save the new state of the page.
- Screenshots will be saved to /screenshots folder.
- Run this command to get the absolute paths of the 2 most recent screenshots in the /screenshots folder:
find screenshots -type f -name "*.png" -exec stat -f "%m %N" {} \; | sort -nr | head -n 2 | awk '{print $2}' | xargs realpath | awk 'NR==1 {print "before path: ", $0} NR==2 {print "after path: ", $0}'
- Call the mcp_reviewEdit function to have your changes visually reviewed.
- Use the following format for the tool call:
{
"beforeScreenshotPath": string, // Absolute path to the second-most recent screenshot
"afterScreenshotPath": string, // Absolute path to the most recent screenshot
"editRequest": string // Describe the edit request from the user in a couple of sentences
}
- You should summarize my edit request into a couple of sentences so that the frontend reviewer understands the changes you made.
- The tool will either return "yes" if your changes are good, or "no" with a brief explanation if the changes don't satisfy the edit request. Keep editing with the same process until the reviewer returns "yes".
Tips
Make sure YOLO mode is on and MCP tools protection is off in your Cursor settings for the best experience.
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。