Skip to main content

Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

Project description

Cursor Feedback MCP

🔧 本项目说明

感谢原作者开源了增强的反馈项目。但是有严重bug未修复。

感谢原作者的反馈项目修复了以下问题并新增功能(但是没有发布pypi):

✅ 已修复问题

  1. 超时设置问题:修复了超时时间永远是 600s 的问题,现已修复默认 24 小时超时 ,可以长时间等待反馈啦
  2. 图片上传问题:修复了无法上传图片报错序列号错误的问题,现已支持更多类型图 片 😁🎉
  3. 断网重连功能:新增断网不断链接功能,现在可以离线同一个会话等待(适合使用 手机热点为电脑提供互联网的场景)

本项目实现的内容

  1. 发布pypi包,方便无缝集成cursor(uvx),无需本地另外安装

📦 安装方式

方式一:从 PyPI 安装(推荐)

最简单的使用方式是通过 uvx 直接运行:

# 使用最新版本
uvx cursor-feedback-mcp@latest

# 使用指定版本
uvx cursor-feedback-mcp@2.6.1

在 Cursor 中配置:

{
  "mcpServers": {
    "cursor-feedback-mcp": {
      "command": "uvx",
      "args": ["cursor-feedback-mcp@latest"],
      "timeout": 86400,
      "env": {
        "MCP_DEBUG": "false",
        "MCP_WEB_HOST": "127.0.0.1",
        "MCP_WEB_PORT": "8765",
        "MCP_DESKTOP_MODE": "false",
        "MCP_LANGUAGE": "zh-CN"
      },
      "autoApprove": ["interactive_feedback"]
    }
  }
}

方式二:本地开发安装

如果需要本地定制开发,可以 Fork 本项目到本地:

# 克隆项目
git clone https://github.com/yourusername/cursor_feedback_mcp.git
cd cursor_feedback_mcp

# 激活虚拟环境(使用 uv)
uv venv
source .venv/bin/activate  # Linux/macOS
# 或
.venv\Scripts\activate  # Windows

# 安装依赖
uv sync

在 Cursor 中配置本地版本:

{
  "mcpServers": {
    "cursor-feedback-mcp-local": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/your/cursor_feedback_mcp",
        "python",
        "-m",
        "mcp_feedback_enhanced"
      ],
      "timeout": 86400,
      "env": {
        "MCP_DEBUG": "false",
        "MCP_WEB_HOST": "127.0.0.1",
        "MCP_WEB_PORT": "8765",
        "MCP_DESKTOP_MODE": "false",
        "MCP_LANGUAGE": "zh-CN"
      },
      "autoApprove": ["interactive_feedback"]
    }
  }
}

注意:请将 /path/to/your/cursor_feedback_mcp 改为您本地的项目位置,这样可以实现本地高自由度的定制。

🚀 发布到 PyPI

如果您想发布自己的版本到 PyPI:

1. 准备工作

确保已安装必要的工具:

uv add --dev twine build

2. 配置 PyPI 凭证

创建 ~/.pypirc 文件:

[distutils]
index-servers =
    pypi

[pypi]
username = __token__
password = pypi-your-api-token-here

3. 构建和发布

# 清理旧的构建文件
rm -rf dist/ build/ *.egg-info

# 构建包
uv build

# 检查构建的包
twine check dist/*

# 上传到 PyPI
twine upload dist/*

4. 测试安装

# 测试从 PyPI 安装
uvx cursor-feedback-mcp@latest

📸 界面预览

MCP Feedback Enhanced 界面预览
主界面 - 支持提示管理、自动提交、会话跟踪上传图片等功能
MCP Feedback Enhanced 功能展示
超时功能展示 - 智能工作流程和现代化体验

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

cursor_feedback_mcp-2.6.1.tar.gz (11.2 MB view details)

Uploaded Source

Built Distribution

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

cursor_feedback_mcp-2.6.1-py3-none-any.whl (8.7 MB view details)

Uploaded Python 3

File details

Details for the file cursor_feedback_mcp-2.6.1.tar.gz.

File metadata

  • Download URL: cursor_feedback_mcp-2.6.1.tar.gz
  • Upload date:
  • Size: 11.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.4

File hashes

Hashes for cursor_feedback_mcp-2.6.1.tar.gz
Algorithm Hash digest
SHA256 f278b1448d6ab5ece9b66f3719bc582b2cbe583739171d044cfa5fb00de23b4b
MD5 afcab91fd4c2ebdbe797ffb130e8ad16
BLAKE2b-256 59fa87cffc31fd440692bdb8765ae6476525c282ecec5b201b56768714d2b6ee

See more details on using hashes here.

File details

Details for the file cursor_feedback_mcp-2.6.1-py3-none-any.whl.

File metadata

File hashes

Hashes for cursor_feedback_mcp-2.6.1-py3-none-any.whl
Algorithm Hash digest
SHA256 26e2a115a3590cc490bef2de4e41d6bbd88e152d7fb1da8c307b454b46b6643c
MD5 cc9cdfa580ea5b8a7e000e760e1d8bf9
BLAKE2b-256 24dfbec68205fca45aff52fdaa20583bae166f92689e9f46607b3dda7e8a5585

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