How do I use lxmusic?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@lxmusic search for 'Yesterday' by The Beatles" 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.

lxmusic

by tiancheng91

Overview Schema Source Related Servers Score Discussions

Python

Features

多音源 — QQ音乐（tx）、网易云（wy）、本地文件扫描（local）
搜索 — 音乐 / 专辑，音源间自由切换
播放 — 获取播放直链或本地路径，--json 含歌词
下载 — 单曲 / 整张专辑下载，带进度条，自动降级音质
歌单 — YAML 存储，创建、搜索添加（多选）、查看、播放、导出 M3U8
本地源 — 扫描音乐目录，同时解析 YAML 歌单文件，search album 按歌单名匹配
配置 — lxmusic config set 运行时修改，只需关心 data_dir + music_dir
MCP — 标准 MCP server（搜索/播放工具）
多音质 — 128k / 320k / FLAC / Hi-Res，不可用时自动降级

Related MCP server: netease-mcp

Quick Start

# 安装
uv tool install lxmusic
# 或: pipx install lxmusic

# 设置 API 密钥（从 https://source.shiqianjiang.cn/ 获取）
lxmusic config set api_key your_key_here

# 搜索音乐（QQ音乐）
lxmusic search music "周杰伦"

# 搜索音乐（网易云）
lxmusic search music "周杰伦" --source wy

# 搜索专辑
lxmusic search album "范特西"

# 播放，返回 URL 和歌词
lxmusic play 102065756 --json

# 下载单曲
lxmusic download 102065756 --dir ~/Music

# 下载整张专辑（先搜索得到 album_id，再下载）
lxmusic album 003DFRzD192KKD --dir ~/Music/七里香

# 启动 MCP server
lxmusic mcp

Installation

从 PyPI

uv tool install lxmusic
# 或: pipx install lxmusic

从源码

git clone <repo-url>
cd lxmusic
uv sync

CLI Usage

Search

lxmusic search music "儿歌" --page 1
lxmusic search album "范特西"
lxmusic search music "周杰伦" --source wy --json
lxmusic search album "我的最爱" --source local      # 本地歌单匹配

Play

lxmusic play 102065756
lxmusic play 102065756 --quality flac
lxmusic play 102065756 --json

{
  "url": "http://...mp3",
  "quality": "320k",
  "lyric": "[ti:七里香]\n...",
  "song": { "id": 102065756, "title": "七里香", "artist": "周杰伦", ... }
}

Download

lxmusic download 102065756                          # 当前目录
lxmusic download 102065756 --dir ~/Music             # 指定目录
lxmusic download 509781655 --source wy --dir ~/Music # 网易云歌曲

Album

lxmusic album 003DFRzD192KKD                          # 远程专辑
lxmusic album "巧虎儿歌" --source local                 # 本地歌单曲目
lxmusic album 003DFRzD192KKD --dir ~/Music/七里香       # 指定目录
lxmusic album 003DFRzD192KKD --quality flac             # 无损音质
lxmusic album 003DFRzD192KKD --json                     # JSON 输出

Playlist

lxmusic playlist create "我的最爱"
lxmusic playlist add "我的最爱" "周杰伦 七里香"          # 搜索 → 交互选择 → 下载 → 添加
lxmusic playlist add "我的最爱" "周杰伦 晴天"             # 回车=全部，逗号分隔多选
lxmusic playlist show "我的最爱"
lxmusic playlist play "我的最爱"
lxmusic playlist export "我的最爱" --dir ~/Music          # 导出 M3U8

Config

lxmusic config set api_key your_key_here                 # 设置密钥
lxmusic config set default_source local                  # 默认本地源
lxmusic config set music_dir ~/Music                     # 音乐文件目录
lxmusic config set data_dir ~/.config/lxmusic             # 数据目录
lxmusic config set default_quality flac                   # 默认音质
lxmusic config set api_key ""                             # 删除配置项
lxmusic config show                                       # 查看当前配置

MCP Server

标准 MCP

lxmusic mcp

标准工具：search_music, search_album, play_music

Local Source

本地源支持两种资产：

音频文件 — .mp3 .flac .wav .m4a .ogg .wma，按文件名搜索
歌单 YAML — 目录下 *.yaml 文件，解析 name + tracks 结构，通过 search album 匹配歌单名

YAML 格式示例（巧虎儿歌.yaml）：

name: 巧虎儿歌
tracks:
  - {"id": 1, "title": "小毛驴", "artist": "儿童歌曲", "path": "/music/小毛驴.mp3"}
  - {"id": 2, "title": "粉刷匠", "artist": "儿童歌曲", "path": "/music/粉刷匠.mp3"}

Configuration

配置项说明

优先级：环境变量 > config.yaml > 默认值

Environment Variable	Description	Default
`LX_MUSIC_API_KEY`	API 密钥（必填）	—
`LX_MUSIC_API_URL`	后端 API 地址	`https://source.shiqianjiang.cn/api/music`
`LX_MUSIC_DEFAULT_SOURCE`	默认音源（tx/wy/local）	`tx`
`LX_MUSIC_DEFAULT_QUALITY`	默认音质（128k/320k/flac/hires）	`320k`
`LX_MUSIC_DATA_DIR`	lxmusic 数据目录	`~/.config/lxmusic`
`LX_MUSIC_MUSIC_DIR`	本地音乐目录（逗号分隔多目录）	`~/.config/lxmusic/library`

目录结构

用户只需要关心两个路径：数据放哪 和 音乐文件在哪，其余子目录自动推导：

data_dir/                    # lxmusic 数据目录（默认 ~/.config/lxmusic）
├── config.yaml              # 配置文件
├── playlists/               # 歌单 YAML 文件
├── cache/                   # 下载缓存（playlist add 下载的音频）
├── library/                 # 曲库索引
└── history/                 # 播放历史

music_dir/                   # 用户音乐文件目录（可多个，逗号分隔）
└── 巧虎儿歌/
    ├── *.mp3
    └── 巧虎儿歌.yaml        # 歌单文件（自动识别）

配置示例

# ~/.config/lxmusic/config.yaml
api_key: your_key_here
api_url: https://source.shiqianjiang.cn/api/music
default_source: local          # 默认使用本地源
default_quality: 320k
data_dir: ~/.config/lxmusic     # 数据目录
music_dir: ~/Music,/mnt/music  # 本地音乐目录（多个用逗号分隔）

常用命令

# 查看当前配置
lxmusic config show

# 设置 API 密钥
lxmusic config set api_key your_key_here

# 切换默认音源
lxmusic config set default_source local

# 设置本地音乐目录（支持多个）
lxmusic config set music_dir "~/Music,/mnt/music"

# 改变数据目录
lxmusic config set data_dir ~/.config/lxmusic

# 删除配置项（恢复默认）
lxmusic config set api_key ""

路径说明

playlist_dir → data_dir/playlists/ — lxmusic playlist 命令操作的文件
cache_dir → data_dir/cache/ — lxmusic playlist add 下载的音频缓存
local_dirs → music_dir 的值 — LocalSource 扫描的目录
lxmusic download 默认下载到当前目录，--dir 指定其他位置

Build & Publish

uv build
uv publish

License

MIT

Available Tools

3 tools

play_musicD

ParametersJSON Schema

Name	Required	Default
`source`	No
`quality`	No	320k
`song_id`	No
`songmid`	No

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_albumD

ParametersJSON Schema

Name	Required	Description	Default
`page`	No
`query`	Yes
`source`	No

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_musicD

ParametersJSON Schema

Name	Required	Description	Default
`page`	No
`query`	Yes
`source`	No

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

3 tool updatesv0.3.0Aug 11, 2026
- First observedplay_music
- First observedsearch_album
- First observedsearch_music

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.1/5.0

Disambiguation5/5

Each tool targets a distinct resource or action: search_music finds tracks, search_album finds albums, and play_music plays a selected item. Names clearly differentiate the purposes, so an agent can easily select the right tool.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: search_music, search_album, play_music. No mixed conventions, making the API predictable.

Tool Count4/5

With 3 tools, the server is minimal but well-scoped for its apparent purpose of music search and playback. It sits at the lower end of the ideal range but each tool earns its place.

Completeness4/5

The core workflow is covered: search for music or albums, then play. Minor gaps like pause/stop or playlist management are absent, but these may be outside the intended scope.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp-sunoOAuth
io.github.AceDataCloud
MCP server for Suno AI music generation, lyrics, and covers
Audio Processing Multimedia Processing Entertainment & Media
248
mcp-producerOAuth
io.github.AceDataCloud
MCP server for Producer/Riffusion AI music generation
Audio Processing AI & Machine Learning
22
RU Books MCP
io.github.books-service
MCP server for Russian books search, details, and recommendation candidates.
Search Art & Culture Entertainment & Media
2
China Hot Trending MCP A
cn.pianam.mcp
MCP server aggregating hot-search boards from 8 Chinese platforms (Weibo, Zhihu, Bilibili, Douyin).
Social Media Web Scraping
21

Related MCP Servers

netease-music-mcp
Entertainment & Media Command Line
luuu-h
A
license
A
quality
D
maintenance
MCP server for controlling local music playback via NetEase Cloud Music, enabling search, play, pause, skip, and lyrics display through a local web player.
Updated 4 months ago (2026-05-06 22:13 UTC)
13
76
MIT
netease-mcp
Entertainment & Media Search
xiaocaoooo
A
license
Not graded
quality
D
maintenance
MCP server that enables AI assistants to search and retrieve music data (songs, lyrics, playlists, albums, artists) from Netease Cloud Music.
Updated 7 days ago (2026-08-31 16:32 UTC)
MIT
mcp_music_server
Entertainment & Media Audio Processing
ganyu123456
A
license
Not graded
quality
A
maintenance
MCP server that enables LLMs to search, play, and manage music from multiple platforms (NetEase, QQ, Kugou) and local files, with lyrics retrieval and playback control.
Updated 2 months ago (2026-07-11 10:10 UTC)
MIT
netease-music-mcp
Entertainment & Media Search
YuanYeYouTao
A
license
A
quality
B
maintenance
A read-only MCP server for NetEase Cloud Music data, enabling querying of songs, artists, albums, playlists, lyrics, and user library through tools like search and get details.
Updated a month ago (2026-07-31 10:21 UTC)
15
2
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tiancheng91/lxmusic'

If you have feedback or need assistance with the MCP directory API, please join our Discord server