Cloud Music MCP Server
Click on "Deploy 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., "@Cloud Music MCP Server Play my daily recommended songs."
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.
网易云音乐 MCP 服务器
基于 网易云音乐开发平台 标准 API 实现
🎵 为您的 AI Agent 插上音乐的翅膀
这是一个基于 网易云音乐 官方API 的本地MCP服务器。可以让用户通过 Claude Code, OpenCode 等 AI Agent以原生 API 的方式点歌!
📢 Update
2026-06-29 🎉 新增歌单管理 — AI 现在可以帮你创建歌单并批量添加歌曲,一句话完成「搜歌 → 建单 → 加歌」全流程。
2026-06-29 🔎 新增资料查询 — 支持查询歌单详情、专辑信息、歌手信息以及你的收藏列表。
2026-06-16 🔧 修复安装问题 — 替换已失效的 PyPI pyncm 为自维护 fork,补齐 build-system,并清除误提交的登录态等敏感文件。
Related MCP server: netease-desktop-mcp
✨ 功能特性
🤖 让 AI Agent 为你播放音乐:通过自然语言指令控制音乐播放。只需说“给我放首热血的歌”,Agent 就会为你搞定一切。
🔓 扫码登录:支持使用手机 App 扫码安全登录。登录状态(Cookies)仅保存在本地,保护您的隐私。
🧠 个性化推荐:完美接入您的每日推荐和歌单。Agent 会根据您的听歌品味来播放音乐。
🔍 搜歌功能:支持按关键词搜索歌曲、歌手或专辑,并直接播放。
📝 歌单管理:不只是放歌,还能帮你创建歌单、批量加歌。说一句"建个某个主题的歌单",AI 就会自动搜歌、建单、加歌一气呵成。
🎛️ 桌面端联动:通过 URL Scheme 唤起网易云音乐客户端播放,无缝衔接原生体验。
🛠️ 工具列表
本服务器向 AI Agent 暴露以下工具:
工具名称 (Tool Name) | 参数 (Parameters) | 功能描述 (Description) |
| 无 | 启动扫码登录流程 (模拟官方 App)。 |
| 无 | 检查当前登录状态和用户信息。 |
| 无 | 获取今日推荐歌曲列表。 |
| 无 | 获取用户的所有歌单(包括创建的和收藏的)。 |
|
| 获取歌单详情及歌单内所有歌曲。 |
|
| 创建新歌单。 |
|
| 批量添加歌曲到指定歌单。 |
|
| 按关键词搜索歌曲、专辑、歌手或歌单。 |
|
| 获取专辑详情及歌曲列表。 |
|
| 获取歌手详情和热门歌曲 Top 10。 |
|
| 获取收藏的歌手或专辑列表。 |
|
| 播放指定的歌曲或歌单(自动唤起桌面应用)。 |
🚀 安装与使用
前置条件
操作系统:macOS 或 Windows
Python 版本:3.10 或更高
macOS:通常自带,运行
python3 --version检查Windows:从 python.org 下载安装
安装网易云音乐桌面客户端(
LLM 客户端(如 Claude Desktop、OpenCode 等)
安装步骤
1. 安装 uv 包管理器
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows (PowerShell)
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"2. 克隆项目并安装依赖
# 克隆项目
git clone https://github.com/Code-MonkeyZhang/cloud-music-mcp.git
cd cloud-music-mcp
# 创建虚拟环境
uv venv
# 激活虚拟环境
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\activate # Windows
# 安装项目(可编辑模式)
uv pip install -e .配置 LLM 客户端
Claude Desktop
找到配置文件:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%/Claude/claude_desktop_config.json
添加以下配置:
{
"mcpServers": {
"cloud-music": {
"command": ["/绝对路径到/cloud-music-mcp/.venv/bin/cloud-music-mcp"],
"enabled": true
}
}
}重要:将
/绝对路径/到/cloud-music-mcp替换为项目的实际绝对路径。Windows 用户请使用双反斜杠\\或正斜杠/。
开启日志(可选)
如需调试,可在配置中添加环境变量:
{
"mcpServers": {
"cloud-music": {
"command": ["/绝对路径/到/cloud-music-mcp/.venv/bin/cloud-music-mcp"],
"enabled": true,
"env": {
"MCP_LOG_ENABLE": "true"
}
}
}
}日志说明:
默认状态:日志功能默认关闭
开启后:日志会以
session_YYYYMMDD_HHMMSS.log的格式保存在项目根目录的logs/文件夹中
使用方法
重启 LLM 客户端(如 Claude Desktop)
登录网易云音乐
在对话中输入:"帮我扫码登录网易云音乐"
AI 会调用
cloud_music_login工具,弹出二维码用手机网易云 App 扫码登录
登录状态(Cookies)仅保存在本地,保护隐私
开始使用
播放音乐:"给我放首歌"
获取推荐:"看看今日推荐有什么"
搜索歌曲:"搜一下周杰伦的歌"
创建歌单:"帮我建个周杰伦热门歌曲的歌单"
播放歌单:"播放我的收藏歌单"
Available Tools
12 toolscloud_music_add_to_playlistC
添加歌曲到指定歌单 args: playlist_id: 目标歌单 ID track_ids: 要添加的歌曲 ID 列表,例如 [123, 456]
Inputs: track_ids (required), playlist_id (required).
cloud_music_album_infoB
获取专辑详情,包括专辑信息和歌曲列表 args: album_id: 专辑 ID
Inputs: album_id (required).
cloud_music_artist_infoB
获取歌手详情和热门歌曲 Top 10 args: artist_id: 歌手 ID
Inputs: artist_id (required).
cloud_music_create_playlistC
创建新歌单 args: name: 歌单名称 privacy: 是否设为隐私歌单,默认为 False
Inputs: name (required), privacy.
cloud_music_get_daily_recommendA
获取今日推荐歌曲 返回歌曲列表 (包含 ID, 歌名, 歌手)
Inputs: no named parameters.
cloud_music_loginA
登录网易云音乐 (模拟 OAuth 流程) 调用此工具后,电脑会弹出一张二维码图片。 请用网易云音乐 App 扫描该二维码。 扫描成功后,工具会自动保存登录状态。
Inputs: no named parameters.
cloud_music_my_playlistsA
获取我的歌单 (包括创建的歌单和红心歌单)
Inputs: no named parameters.
cloud_music_my_subscriptionsA
获取我收藏的歌手或专辑 args: category: 类型,'artists'(歌手) 或 'albums'(专辑),默认为 'artists'
Inputs: category.
cloud_music_playA
唤起客户端播放指定歌曲或歌单 args: id: 歌曲ID 或 歌单ID type: 'song' (单曲) 或 'playlist' (歌单)
Inputs: id (required), type.
cloud_music_playlist_detailC
获取歌单详情,包括歌单内所有歌曲 args: playlist_id: 歌单 ID
Inputs: playlist_id (required).
cloud_music_searchA
搜索歌曲、专辑、歌手或歌单 args: keyword: 搜索关键词(歌名、歌手名、专辑名等) category: 搜索类型,可选 'song'(歌曲)、'album'(专辑)、'artist'(歌手)、'playlist'(歌单),默认为 'song'
Inputs: keyword (required), category.
cloud_music_statusA
检查网易云音乐当前是否已登录
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Every tool has a clearly distinct purpose, from login and search to playlist management and playback. There is no ambiguity between tools.
All tools follow a consistent 'cloud_music_' prefix with snake_case verb_noun pattern (e.g., add_to_playlist, create_playlist, get_daily_recommend), making naming predictable.
12 tools are appropriate for a cloud music server, covering search, details, playlist management, login, and playback. Slightly over the ideal range but each tool earns its place.
Core workflows like search, get details, create playlist, add tracks, and play are covered. However, notable gaps exist: no tools to remove tracks, delete playlists, or manage likes, limiting full lifecycle coverage.
Maintenance
Related MCP Connectors
Music industry tools for AI agents: artist research, catalogs, release plans and content.
Generate full songs with vocals, instrumentals and sound effects from text. One server for Suno, Google Lyria, Mureka, MiniMax, ACE-Step, YuE and ElevenLabs. Your agent can quote the credit cost before generating, start a song, wait for it to finish and return download links. Sign in with OAuth; optional daily credit caps; retries never charge twice.
Spotify MCP server for ChatGPT, Claude and any AI agent: search songs and artists, list playlists, read playlist songs, create playlist, add songs to playlist, remove songs from playlist, set playlist public or private and save to Liked Songs in your own Spotify account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Spotify yourself; Cotlet does not store your password and you need no Spotify API key. About the official Spotify API: Spotify has a full Web API and, since 23 Apr 2026, an official connector for Claude (checked 5 Nov 2026). The API needs an app you register, and in development mode the app owner must have Premium and the app allows 5 users; unlimited users need a registered business with at least 250,000 monthly users. Setup and FAQ: https://cotlet.dev/integrations/spotify-api-mcp-server
660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceControls the official NetEase Cloud Music desktop client on Windows, enabling AI to search, play, manage queues, and adjust playback settings via a local control channel.1MIT
- AlicenseAqualityBmaintenanceEnables AI clients to control the Windows NetEase Cloud Music desktop app via local stdio MCP, including reading current song and liked state, searching and playing tracks, playback control, track skipping, and setting the current song's liked status.10MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to control a local NetEase Cloud Music client in natural language — searching songs and playlists, playing or queuing tracks, replacing the queue with a playlist, and pausing, skipping, or adjusting volume — via a BetterNCM plugin and localhost bridge with token authentication.8 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables ChatGPT and Codex to read and curate a NetEase Cloud Music account's recommendations, playlists, listening history, and podcasts, and to perform safely bounded, audited account writes, with optional macOS playback and iPhone Listen Together controls.MIT