MCP Chrome Feedback

- 🤖交互式反馈收集: 通过Chrome扩展界面收集用户反馈
- 📝文本和图片支持: 支持文本反馈和图片附件
- 🔄实时通信: WebSocket实时通信机制
- 📊反馈历史: 自动保存和管理反馈历史
- 🎯元素捕获: 支持页面元素捕获和截图
- ⚡即插即用: 标准MCP协议，可直接配置到Cursor

Minidoracat-mcp-feedback-enhancedweb-infra-dev-midscene-chrome-extension

{ "mcpServers": { "chrome-feedback": { "command": "npx", "args": ["mcp-chrome-feedback@latest"] } } }

npm install -g mcp-chrome-feedback@latest

git clone https://github.com/2019-02-18/MCX.git cd MCX/mcp-chrome-feedback npm install npm run build

# 构建项目 npm run build # 开发模式 npm run dev # 清理构建文件 npm run clean

- 打开Chrome浏览器
- 进入chrome://extensions/
- 开启"开发者模式"
- 点击"加载已解压的扩展程序"
- 选择项目中的chrome-extension文件夹

{ "mcpServers": { "chrome-feedback": { "command": "npx", "args": ["mcp-chrome-feedback@latest"] } } }

{ "mcpServers": { "chrome-feedback": { "command": "mcp-chrome-feedback" } } }

{ "mcpServers": { "chrome-feedback": { "command": "npx", "args": ["mcp-chrome-feedback@latest"], "env": { "MCP_CHROME_PORT": "8900" } } } }

{ "mcpServers": { "chrome-feedback": { "command": "node", "args": ["/path/to/MCX/mcp-chrome-feedback/build/index.js"] } } }

- 确保Chrome扩展已安装并启用
- 打开扩展的侧边栏
- 点击"连接"按钮连接到MCP服务

- summary: AI工作摘要 (默认: "我已完成了您请求的任务。")
- timeout: 超时时间(秒) (默认: 600)
- project_directory: 项目目录 (默认: ".")
- AI请求反馈: 在Cursor中调用interactive_feedback工具
- 扩展显示界面: Chrome扩展自动显示反馈收集界面
- 用户提供反馈: 用户输入文本、上传图片或捕获页面元素
- 反馈传回AI: 反馈数据通过MCP协议传回Cursor
- AI处理反馈: AI根据反馈调整后续行为

- MCP_CHROME_PORT: Chrome扩展通信端口 (默认: 8797，如端口被占用会自动递增到可用端口)

- 服务会自动寻找可用端口 (8797-8806)
- 如需指定端口，使用环境变量MCP_CHROME_PORT
- 清理npx缓存:rm -rf ~/.npm/_npx(Unix) 或删除%USERPROFILE%\.npm\_npx(Windows)

- 确保使用最新版本:mcp-chrome-feedback@latest
- 清理npm缓存:npm cache clean --force
- 超时设置: 增加timeout参数值
- 网络连接: 检查本地网络连接
- 扩展权限: 确认扩展有必要的权限

- 🚀重大改进: 升级MCP SDK到v1.13.0
- 🔧端口管理: 添加自动端口分配功能 (8797-8806)
- 🛠️依赖修复: 解决npx安装和运行问题
- 📦打包优化: 改进npm包结构和依赖管理
- 🐛错误处理: 增强错误日志和调试信息

- 🔄端口冲突修复: 初步解决端口占用问题
- 📝文档更新: 改进安装和配置说明

- 🎉初始版本: 基础反馈收集功能
- 🔌Chrome扩展集成: 完整的浏览器扩展支持
- 🤖MCP协议支持: 标准MCP工具实现
- 💬实时通信: WebSocket双向通信

Manage your WhatsApp, SMS and Phone Calls using a single MCP connector

Connect to any function, any language, across network boundaries using AgentRPC.

Access your meeting transcripts, summaries, and action items from any AI assistant.

Connect Claude, ChatGPT, and other AI tools to your Granola meeting notes via MCP. Query your notes, search transcripts, and get meeting insights in your favorite AI assistants.

Build with the Kudosity API to send SMS and MMS. Access developer docs, API references and live testing tools to send messages, manage contact lists, configure webhooks and more.

Send SMS, WhatsApp, and RCS messages programmatically with DLT compliance. Manage contacts, schedule campaigns, and track delivery reports.

Interact with Twilio APIs to send messages, manage phone numbers, configure your account, and more.

The VoIPstudio MCP server gives compatible AI assistants secure access to authorised VoIPstudio account data, including recordings, call detail records, live calls and voicemails in order to query call activity, analyse patterns, identify agent performance issues and generate QA or operations reports in plain English.

A bridge server connecting Agent Communication Protocol (ACP) agents with Model Context Protocol (MCP) clients.