SkillAgentSearch skills...

music-creation-engine

AI-Powered Full-Pipeline Music Composition Engine — Multi-Agent Lyric Writing → Sheet Music (PDF/MIDI/MusicXML) → Demo Audio (MP3) → Quality Eval → Publish. Zero GPU required. AI coding agent native. / AI 驱动全链路音乐创作引擎 — 多Agent作词→乐谱→Demo→评估→发布。零GPU。AI智能体原生。

Install / Use

claude mcp add mage0535 -- npx -y github:mage0535/music-creation-engine

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

74/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of music-creation-engine

music-creation-engine scores 74/100 on our quality scale, 2630th of 2,893 Automation skills we index.

Its MCP Server is 3.2 KB long, well organised into 16 sections with 5 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 78/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

music-creation-engine compared with similar skills

All 4 of these similar skills score higher than music-creation-engine; compare them before choosing.

SkillScoreStarsUpdatedFormat
music-creation-engine (this skill)by mage05357433mo agoMCP Server
Agent-Reachby Panniantong100100.1ktodayCLAUDE.md
headroomby headroomlabs-ai10076.5ktodayCLAUDE.md
CowAgentby zhayujie10047.5ktodayCLAUDE.md
Scraplingby D4Vinci10088.8k1d agoMCP Server

Frequently asked questions

How do I install music-creation-engine?
Run claude mcp add mage0535 -- npx -y github:mage0535/music-creation-engine. The install tabs above show the steps for each supported agent.
Which AI agents does music-creation-engine work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is music-creation-engine safe to use?
It declares no license and scores 78/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is music-creation-engine still maintained?
The repository was last updated about 3 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

Music Creation Engine

English | 中文

music-creation-engine 是一个面向 Hermes、Codex、OpenClaw 等智能体的音乐执行引擎。它负责把智能体已经决定好的结构化音乐方案,落地成可验证、可交付的产物,而不是自己承担对话式创作判断。

一句话定位

Agent 负责“想”,Engine 负责“做”。

  • Agent:理解用户需求,推理风格、段落、旋律、和声、乐器分工
  • Engine:生成 MIDI、MusicXML、LilyPond、PDF、WAV、MP3,并管理工作流产物

当前版本

  • 当前发布版本:v0.4.0
  • 当前开发重点:v0.5.0 工程硬化
  • 项目真相源:references/project-status.md

适用场景

  • 想让智能体真正产出音乐文件,而不是只给一段文本建议
  • 想把作曲、渲染、修订、重试、产物管理做成稳定工作流
  • 想让 Hermes / Codex / OpenClaw 共用同一套音乐执行层
  • 想保留结构化输入和可重复验证的工程边界

核心能力

  • 结构化作曲:key、bpm、chord_progression、sections、melody、instrument_roles
  • 乐谱产物:MIDI、MusicXML、LilyPond、PDF
  • 音频产物:WAV、MP3
  • 工作流生命周期:status、revise、retry、cancel、delete、cleanup
  • MIDI 工具:diff、diff-files、inspect、query、transform
  • 可演奏性检查:钢琴、人声、吉他、贝斯等基础规则
  • 参考检索:Meting 主路径,HTTP fallback 兜底

快速开始

Docker

git clone https://github.com/mage0535/music-creation-engine.git
cd music-creation-engine
docker compose up

手动安装

python3 -m pip install -e .
sudo apt-get install -y lilypond fluidsynth fluid-soundfont-gm ffmpeg
npm install -g @eldment/meting-agent
uvicorn music_creation_engine.api.app:create_app --factory --host 0.0.0.0 --port 8000

最小工作流

  1. 调用 GET /health 和 GET /capabilities 确认服务可用
  2. 用 POST /v1/score 生成乐谱与 MIDI
  3. 用 POST /v1/render 或 POST /v1/workflows/full 生成音频与完整产物
  4. 用 POST /v1/workflows/{id}/revise 做修订迭代
  5. 用 GET /v1/artifacts/{id} 和 GET /v1/artifacts/{id}/files/{name} 取回结果

认证与限流

v0.5.0 工程硬化已经落地基础认证与限流能力:

  • MCE_API_KEYS:逗号分隔的 API key 列表
  • MCE_RATE_LIMIT_PER_MINUTE:每分钟限流阈值
  • MCE_AUTH_HEADER_NAME:自定义鉴权头,默认 x-api-key

如果未配置 MCE_API_KEYS,本地开发默认不强制鉴权。
如果配置了 MCE_API_KEYS,所有 /v1/* 路由都需要携带 API key。

示例请求

{
  "lyrics": "Verse text",
  "output_base": "build/output/song",
  "key": "Am",
  "bpm": 72,
  "instruments": "piano,vocals,bass,drums",
  "style": "pop",
  "chord_progression": ["Am", "F", "C", "G"],
  "sections": [
    {"name": "intro", "bars": 4},
    {"name": "verse", "bars": 8},
    {"name": "chorus", "bars": 8}
  ],
  "melody": {"vocals": ["A4", "B4", "C5", "A4"]},
  "instrument_roles": {"piano": "chord", "bass": "bass", "vocals": "melody", "drums": "rhythm"}
}

主要接口

  • GET /health
  • GET /capabilities
  • POST /v1/score
  • POST /v1/render
  • POST /v1/workflows/full
  • GET /v1/workflows/{workflow_id}/status
  • POST /v1/workflows/{workflow_id}/revise
  • POST /v1/references/search
  • POST /v1/midi/inspect
  • POST /v1/playability

文档入口

  • 项目真相源:references/project-status.md
  • 当前状态:references/current-state.md
  • 连续开发记录:references/continuous-development.md
  • 发布说明:references/release-notes-v0.4.0.md
  • 版本变更:CHANGELOG.md

测试

python -m pytest -q tests --ignore=tests/live_service_test.py
python tests/e2e_http_workflow.py

项目结构

config/                         默认配置
src/music_creation_engine/      主包源码
adapters/                       Hermes / Codex / OpenClaw 适配
references/                     状态、路线图、开发文档
tests/                          单测、集成测试、E2E
Dockerfile
docker-compose.yml
install.sh

下一步

当前建议顺序:

  1. 先稳住文档真相源和工程边界
  2. 再推进 v0.5.0 的认证、CI、smart revision、真实 integration test
  3. 最后再进入 midi-composer-mcp、SSE、Reaper 深集成等能力扩展

Related Skills

View on GitHub
GitHub Stars3
CategoryAutomation
Updated3mo ago
Forks0

Languages

Python

Trust signals

78/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low1 info