Skip to main content

MCP server for interactive feedback collection in AI-assisted development workflows.

Project description

mcp-interactive

English | 简体中文

MCP 服务器,用于在 AI 辅助开发过程中收集用户的交互式反馈。通过引导 AI 与用户确认而非自行猜测,减少不必要的工具调用,降低平台成本,提高开发效率。

mcp-interactive Web UI

工作流程

  1. AI 调用 interactive_feedback 工具
  2. 自动打开浏览器界面(Web UI)
  3. 用户输入反馈文本、上传截图、选择常用提示词
  4. 通过 WebSocket 实时传递给 AI
  5. AI 根据反馈调整行为或结束任务

安装

pip install uv

配置

将以下内容添加到 MCP 配置文件:

{
  "mcpServers": {
    "mcp-interactive": {
      "command": "uvx",
      "args": ["mcp-interactive@latest"],
      "timeout": 600,
      "autoApprove": ["interactive_feedback"]
    }
  }
}

支持的 AI 平台:Cursor | Cline | Windsurf | Augment | Trae

环境变量

变量 说明 默认值
MCP_WEB_HOST Web UI 监听地址 127.0.0.1
MCP_WEB_PORT Web UI 端口 9766
MCP_LANGUAGE 界面语言 (zh-CN / en) 自动检测
MCP_DEBUG 调试模式 false

SSH 远程开发时,将 MCP_WEB_HOST 设为 0.0.0.0 以允许远程访问,或使用 SSH 端口转发。

功能

  • 提示词管理 - 常用提示词的增删改查和智能排序
  • 自动定时提交 - 1-86400 秒可配置定时器,支持暂停/恢复
  • 图片上传 - 拖放、粘贴,支持 PNG/JPG/GIF/BMP/WebP
  • 多语言 - 简体中文、English,即时切换
  • WebSocket 实时通信 - 状态监控、自动重连

开发

git clone https://github.com/RealAlexandreAI/mcp-interactive.git
cd mcp-interactive
uv sync

# 测试
make test          # 单元测试
make test-web      # Web UI 测试

# 代码检查
make check         # 完整检查(lint + format + type)

致谢

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_interactive-0.1.1.tar.gz (11.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_interactive-0.1.1-py3-none-any.whl (8.6 MB view details)

Uploaded Python 3

File details

Details for the file mcp_interactive-0.1.1.tar.gz.

File metadata

  • Download URL: mcp_interactive-0.1.1.tar.gz
  • Upload date:
  • Size: 11.5 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for mcp_interactive-0.1.1.tar.gz
Algorithm Hash digest
SHA256 87dd708303c6df636eaabead4f23faffbf067d5b566635a415f8ed535ae643e5
MD5 32d722708602e745d75505a061b350a0
BLAKE2b-256 8f2c3308db7bd19a06aa75a9e31321dcf8dc06033c61a8fa5241f586de5387ad

See more details on using hashes here.

File details

Details for the file mcp_interactive-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_interactive-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 8f29c618b4a8e93e6f337d7b3cc169a6f3e7b234be4648792c9f90c20346d4ea
MD5 f59db14df4377fa8a42c100e59c8c1ae
BLAKE2b-256 49886c03d34feeb1cf5d83cd66f5a076a22d740abd86e03cac1be96ecf940a58

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page