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

🔧 项目说明

基于 mcp-feedback-enhanced 项目进行定制开发,感谢原作者的贡献!

本版本修复了以下问题并新增功能:

✅ 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)

🚀 如何使用

方式一:使用 uvx 直接安装(推荐)

# 直接使用 uvx 运行
uvx cursor-feedback-mcp

# 或者安装后使用
uv tool install cursor-feedback-mcp
cursor-feedback-mcp

方式二:在 Cursor 中配置

{
  "mcpServers": {
    "cursor-feedback-mcp": {
      "command": "uvx",
      "args": ["cursor-feedback-mcp"],
      "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"]
    }
  }
}

方式三:本地开发模式

Fork 本项目到本地,在 Cursor 中配置:

{
  "mcpServers": {
    "cursor-feedback-mcp-local": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/your/cursor_feedback_mcp",
        "python",
        "-m",
        "cursor_feedback_mcp"
      ],
      "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。

📸 界面预览

Cursor Feedback MCP 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
Cursor Feedback MCP 功能展示
超时功能展示 - 智能工作流程和现代化体验

📦 安装与发布

从 PyPI 安装

# 使用 uvx 直接运行
uvx cursor-feedback-mcp

# 或使用 pip 安装
pip install cursor-feedback-mcp

# 或使用 uv 安装
uv tool install cursor-feedback-mcp

本地开发

# 克隆项目
git clone https://github.com/zhajiahe/cursor-feedback-mcp.git
cd cursor-feedback-mcp

# 安装依赖
uv sync

# 运行测试
uv run pytest

# 本地构建
uv build

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-2.6.2.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-2.6.2-py3-none-any.whl (8.6 MB view details)

Uploaded Python 3

File details

Details for the file cursor_feedback_mcp-2.6.2.tar.gz.

File metadata

  • Download URL: cursor_feedback_mcp-2.6.2.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-2.6.2.tar.gz
Algorithm Hash digest
SHA256 3c790474789db0854489f69ddc231312017f50f041f407073936b9c4ed676510
MD5 8d9072914f21acc8ab26f407fe914c56
BLAKE2b-256 c1d67631e991d4385704ece4701e75b8e2d2c8f85c98dd33be59a2efd2697ff8

See more details on using hashes here.

File details

Details for the file cursor_feedback_mcp-2.6.2-py3-none-any.whl.

File metadata

File hashes

Hashes for cursor_feedback_mcp-2.6.2-py3-none-any.whl
Algorithm Hash digest
SHA256 8266582ca6fdeaf7387bca8811a410456f689dcbecaa4ee678216369c80d57ed
MD5 b9c29527b21743f9db26151125333527
BLAKE2b-256 f4c6d2964c6ffa49ee98b78b25aa392cb7891019c173c12c2309f0adad760fe2

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