Interactive MCP Popup
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Interactive MCP PopupAsk user for feedback on the latest changes."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Interactive MCP Popup
一个现代化的 MCP (Model Context Protocol) 交互服务,支持 Qt 弹窗和持续对话功能。
特性
🎨 现代化 Qt 弹窗 - 直接在 IDE 内显示,无需切换浏览器
💬 持续对话 - 支持多轮对话直到用户选择结束
🌍 跨平台支持 - 支持 Windows 和 macOS
🎯 简洁设计 - 统一的现代化界面风格
⚡ 易于集成 - 简单的 MCP 配置
Related MCP server: Enhanced Interactive Feedback MCP Server
安装
前置要求
Python 3.11+
uv (Python 包管理器)
安装步骤
克隆项目
git clone https://github.com/wangdefaf/interactive-mcp-popup.git
cd interactive-mcp-popup安装依赖
uv sync配置 MCP
在你的 MCP 配置文件中添加:
{
"mcpServers": {
"interactive-mcp-popup": {
"command": "uv",
"args": [
"--directory",
"/path/to/interactive-mcp-popup",
"run",
"src/interactive_mcp_popup/server.py"
],
"timeout": 600,
"autoApprove": [
"ask_user_popup",
"start_conversation",
"continue_conversation",
"end_conversation",
"get_conversation_history",
"test_popup",
"check_dependencies"
]
}
}
}使用方法
配置规则
在任何流程、任务、对话进行时,无论是询问、回复、或完成阶段性任务,皆必须调用 MCP interactive-mcp-popup。
每当收到用户反馈,若反馈内容非空,必须再次调用 MCP interactive-mcp-popup,并根据反馈内容调整行为。
仅当用户明确表示「结束」或「不再需要交互」时,才可停止调用 MCP interactive-mcp-popup,流程才算结束。
除非收到结束指令,否则所有步骤都必须重复调用 MCP interactive-mcp-popup。
完成任务前,必须使用 MCP interactive-mcp-popup 工具向用户询问反馈。
基础弹窗提问
from interactive_mcp_popup import ask_user_popup
result = ask_user_popup(
question="你觉得这个功能怎么样?",
context="这是一个测试问题"
)持续对话
from interactive_mcp_popup import (
start_conversation,
continue_conversation,
end_conversation
)
# 开始对话
conv_id = start_conversation("项目规划讨论")
# 继续对话
response = continue_conversation(conv_id, "你觉得这个设计怎么样?")
# 结束对话
end_conversation(conv_id, "讨论完成")项目结构
interactive-mcp-popup/
├── src/
│ └── interactive_mcp_popup/
│ ├── __init__.py
│ ├── server.py # 主 MCP 服务器
│ ├── popup.py # Qt 弹窗实现
│ ├── conversation.py # 持续对话管理
│ └── utils.py # 工具函数
├── docs/
│ ├── api.md # API 文档
│ ├── configuration.md # 配置说明
│ └── examples.md # 使用示例
├── examples/
│ ├── basic_usage.py # 基础使用示例
│ └── advanced_usage.py # 高级使用示例
├── tests/
│ ├── test_popup.py # 弹窗测试
│ └── test_conversation.py # 对话测试
├── pyproject.toml # 项目配置
├── README.md # 项目说明
├── LICENSE # MIT 许可证
└── .gitignore # Git 忽略文件API 参考
弹窗工具
ask_user_popup(question, context)- 弹窗提问test_popup()- 测试弹窗功能check_dependencies()- 检查依赖
对话工具
start_conversation(topic, context)- 开始对话continue_conversation(conv_id, message)- 继续对话end_conversation(conv_id, summary)- 结束对话get_conversation_history(conv_id)- 获取历史
开发
本地开发
# 安装开发依赖
uv sync --dev
# 运行测试
uv run pytest
# 代码格式化
uv run black src/
uv run isort src/贡献
欢迎提交 Issue 和 Pull Request!
许可证
MIT License - 详见 LICENSE 文件
致谢
本项目思想借鉴了 interactive-feedback-mcp 项目,但代码完全独立实现。
支持
如果你遇到问题或有建议,请:
让 MCP 交互更简单、更直观! 🚀
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceA MCP server that enables human-in-the-loop workflow in AI-assisted development tools by allowing users to run commands, view their output, and provide textual feedback directly to the AI assistant.11,714MIT
- AlicenseBqualityDmaintenanceAn advanced MCP server that provides interactive feedback mechanisms with support for various feedback types, multi-language capabilities, and team collaboration features for AI tools like Cursor, Cline, and Windsurf.41MIT
- Alicense-qualityDmaintenanceA MCP server that enables AI assistants to collect interactive user feedback with text and image support via a modern GUI.236MIT
- Flicense-qualityCmaintenanceAn MCP server that establishes feedback-oriented development workflows with a Web UI and desktop app, allowing users to provide interactive feedback to AI models through prompts, images, and session tracking.
Related MCP Connectors
Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).
MCP server for AI dialogue using various LLM models via AceDataCloud
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/wangdefaf/interactive-mcp-popup'
If you have feedback or need assistance with the MCP directory API, please join our Discord server