AI Skill Hub 推荐使用:编程伴奏DJ 是一款优质的MCP工具。AI 综合评分 7.2 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
创意MCP工具,整合Apple Music音乐库与AI编程环境,为开发者提供智能选歌和卡拉OK功能。通过音乐增强编程体验,适合需要背景音乐陪伴的程序员,打造个性化编码氛围。
编程伴奏DJ 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
创意MCP工具,整合Apple Music音乐库与AI编程环境,为开发者提供智能选歌和卡拉OK功能。通过音乐增强编程体验,适合需要背景音乐陪伴的程序员,打造个性化编码氛围。
编程伴奏DJ 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/jaychempan/coding-with-beat
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"----dj": {
"command": "npx",
"args": ["-y", "coding-with-beat"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 编程伴奏DJ 执行以下任务... Claude: [自动调用 编程伴奏DJ MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"____dj": {
"command": "npx",
"args": ["-y", "coding-with-beat"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
将音乐搬进AI终端 · 打造Coding专属智能DJ · 听歌新范式 · 交互式音乐
When was the last time you sang and danced while vibecoding?(上次 vibecoding 时又唱又跳是什么时候?) Right. You can't remember.(对,你已经不记得了。)

Your coding soundtrack, now inside the terminal. Smart music selection, mood-aware playback, and a pixel DJ that vibes with every keystroke — works with Claude Code, Codex CLI, and any AI-powered terminal.
A retro pixel DJ companion for AI coding sessions. It plays music, shows lyrics, celebrates when you commit, and panics with you when tests fail.
<video src="https://github.com/user-attachments/assets/c51dcac1-115e-4d30-b87f-b1e7043d1347" controls autoplay loop muted width="100%"></video>

<details> <summary>More screenshots</summary>


</details>
💬 We'd love your feedback! Using Coding with Beat? Tell us what you think — features you want, bugs you've hit, or just how it's changed your coding sessions. → Take the 7-min survey (EN / 中文 both supported)
---
/cwb-profile — Music Profile & Listening Reports (dev preview)
A new skill that analyses your play history and search patterns to generate personalised listening reports and recommendations — daily, weekly, monthly, or yearly.
Try it — just say it naturally:
帮我生成本周的听歌报告
生成年度音乐画像
我最近都在听什么?适合写代码的
what have I been listening to this week
The AI calls generate_profile() and returns:
smart_search queries ready to playCLI (works offline, no MCP server needed):
cwb profile # weekly (default)
cwb profile daily
cwb profile monthly
cwb profile yearly
---
/cwb skill — Auto-registered routing brain: mood/vibe → multi-angle smart search, specific song/artist → catalog lookup, "play 3" → play_number. The AI always calls the right tool.| Scene | Say… | |-------|------| | 🎧 Lofi | lofi · 深夜写代码 · chillhop | | 🧠 Focus | 专注 · ambient · flow state | | 🔥 Hype | workout · 充能 · 运动 | | ☕ Jazz | jazz · 咖啡馆 · bossa nova | | 🌆 Synthwave | synthwave · 赛博 · 夜驾 | | 🌅 Relax | 放松 · unwind · 下班 | | 🎹 Classical | 古典 · 钢琴 · classical | | 💙 Sad | 伤感 · heartbreak · 难过 | | 🎉 Party | party · edm · 蹦迪 | | 🏮 Chinese | 国风 · 华语 · 古风 | | 🌙 Sleep | 助眠 · sleep · 白噪音 | - Playlists — List and play your Apple Music playlists (user-created + subscription) directly from the AI: "我有哪些歌单" → numbered list → "播放周杰伦代表作". Queue syncs to cwb watch automatically. - Play history — cwb history / list_history shows your recently played tracks sourced from Apple Music's native played date. history_search recommends new music based on your listening patterns. - Music sources — Apple Music (AppleScript, no GUI needed), local files (afplay), QQ Music (search + preview). - Pixel UI — Album art in half-block ANSI, GameBoy retro border, pseudo-spectrum equalizer. - DJ Buddy — A headphones-wearing pixel character that reacts to your coding state. Tests failing? It panics with you. - Vibe engine — CC hooks track what you're doing in real time and shift the mood. git commit? Victory pose. Tests explode? Panic mode. - Statusline — One line: face + current track + progress bar. - Focus mode — Built-in 25/5 Pomodoro timer shown in the statusline.
---
[!NOTE] Want to try the latest features before release? Check out the dev branch for cutting-edge updates.
./install.sh # for Claude Code ./install_codex.sh # for Codex CLI
./install.sh --mcp-url http://127.0.0.1:8765/mcp # Claude Code ./install_codex.sh --mcp-url http://127.0.0.1:8765/mcp # Codex CLI ```
The remote session, /cwb, statusline, hooks, and cwb CLI all use the same HTTP MCP URL. As long as the SSH tunnel is up, commands like cwb play, cwb np, cwb next, cwb player, and cwb karaoke control the Mac-side music client.
---
```bash
[!TIP] Not sure what to say? Just ask —DJ 能做什么/DJ help— and DJ Buddy will show you a full list of phrases you can use. Live player: Open a second terminal and runcwb watchto see the currently playing track, lyrics, and progress bar in real time. Apple Music: The first time you play a catalog track, a popup will appear — click Add to Library, then repeat the play command.
If your AI CLI runs on a remote server while Apple Music runs on your local Mac, run the streamable HTTP MCP server on the Mac and reach it from the server through SSH reverse port forwarding:
```bash
创意十足的MCP工具,巧妙融合音乐与编程,提升开发体验。实现完整度较高,但生态完善度和用户基数尚需时间检验,具有实验性特征。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,编程伴奏DJ 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | coding-with-beat |
| 原始描述 | 开源MCP工具:🎵(编程伴奏:将音乐搬进AI终端,打造Coding专属智能DJ,智能选歌平台) When was the last time you sang and dan。⭐11 · Python |
| Topics | 音乐集成Claude集成开发者工具MCP协议创意应用 |
| GitHub | https://github.com/jaychempan/coding-with-beat |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-23 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端