Skip to main content
Glama

前端审查-mcp

一个 MCP 服务器,用于对 UI 编辑请求进行可视化审核。请您的客服人员截取编辑前后的页面截图,然后调用此工具来审核编辑结果。

用法

光标

  • 要在项目中安装,请将 MCP 服务器添加到.cursor/mcp.json

{ "mcpServers": { "frontend-review": { "command": "npx", "args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"], } } }
  • 要全局安装,请将此命令添加到您的 Cursor 设置中:

npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key>

风帆冲浪

  • 将 MCP 服务器添加到您的~/.codeium/windsurf/mcp_config.json文件:

{ "mcpServers": { "frontend-review": { "command": "npx", "args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"] } } }

工具

目前,唯一的工具是reviewEdit

您的代理将使用以下参数调用此工具:

  • beforeScreenshotPath :编辑前页面截图的绝对路径。

  • afterScreenshotPath :编辑后页面截图的绝对路径。

  • editRequest :用户提出的 UI 编辑请求的详细描述。

该工具将返回yesno ”的响应,表明该编辑在视觉上是否满足编辑请求。如果“否”,它将提供编辑不满足请求的详细说明,以便您继续进行操作。

审查模型

目前,审核模型是 Hyperbolic 的Qwen/Qwen2-VL-72B-Instruct 。如果审核失败,系统会自动使用以下模型重试请求:

后备顺序:

  1. Qwen/Qwen2-VL-72B-Instruct

  2. Qwen/Qwen2-VL-7B-Instruct

  3. meta-llama/Llama-3.2-90B-Vision-Instruct

  4. mistralai/Pixtral-12B-2409

如果您想使用不同的模型作为第一个模型,您可以将MODEL参数添加到命令中:

npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key> MODEL=<your-model>

它将首先尝试指定的模型,如果失败,则尝试其他模型。

截屏

您可以使用任何 MCP 服务器截屏。我一直在使用https://github.com/AgentDeskAI/browser-tools-mcp ,它有一个takeScreenshot工具,以及其他一些有用的前端开发工具。

AI指令

您可以在 AI 的提示中包含以下说明,以使其截取屏幕截图并审查编辑:

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".

尖端

为获得最佳体验,请确保在光标设置中启用 YOLO 模式并关闭 MCP 工具保护。

Deploy Server
A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

Related MCP Servers

  • A
    security
    A
    license
    A
    quality
    TypeScript-based MCP server designed to enhance code editing experiences by providing features such as hover information, code completion, and diagnostics.
    Last updated -
    3
    25
    MIT License
    • Apple
  • -
    security
    -
    license
    -
    quality
    A Model Context Protocol server that provides AI vision capabilities for analyzing UI screenshots, offering tools for screen analysis, file operations, and UI/UX report generation.
  • A
    security
    F
    license
    A
    quality
    An MCP server that provides web development tools including taking screenshots of screens, enabling AI agents to capture and analyze visual content during development.
    Last updated -
    2
    33
    10
  • -
    security
    A
    license
    -
    quality
    An MCP tool server that enables generating and editing images through OpenAI's image models, supporting text-to-image generation and advanced image editing (inpainting, outpainting) across various MCP-compatible clients.
    Last updated -
    79
    MIT License
    • Linux
    • Apple

View all related MCP servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zueai/frontend-review-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server