OpenUtau-MCP
OpenUtau-MCP 🎤🤖
OpenUtau 및 DiffSinger용 독립형 Model Context Protocol (MCP) 서버
AI 에이전트(Claude Desktop, Cursor, Antigravity, VS Code)가 OpenUtau v0.6+ (.ustx) 프로젝트 파일과 DiffSinger 신경 표현을 직접 생성, 검사, 미세 조정할 수 있게 합니다.
🌟 기능
🛠️ 네이티브
.ustx프로젝트 생성기: Singer ID 및 Phoneticizer 바인딩이 포함된 멀티트랙 YAML 프로젝트 파일을 생성합니다.🎛️ DiffSinger 및 신경 표현 곡선: Dynamics(
dyn), Tension(tns), Breathiness(bre), Vibrato 곡선을 생성합니다.🔍 프로젝트 검사기: 기존
.ustx파일을 파싱하여 트랙 구조, 노트, 메타데이터를 추출합니다.🎶 음향 미리듣기 신시사이저: 25ms 코사인 제곱 크로스페이딩을 사용한 즉시 24-bit PCM 미리듣기 오디오 합성.
⚡ 제로 의존성 코어: 경량 Python stdio JSON-RPC 2.0 서버.
Related MCP server: utauMCP
🚀 빠른 설정
1. 의존성 설치
pip install -r requirements.txt2. 서버 확인
python test_mcp.py3. AI 에이전트 구성(mcpSettings.json)에 추가
{
"mcpServers": {
"openutau-mcp": {
"command": "python",
"args": ["F:/antigravity lol/github项目/OpenUtau-MCP/server.py"]
}
}
}📄 라이선스
MIT 라이선스 (c) 2026 turboegg1145
This server cannot be deployed
Maintenance
Related MCP Connectors
Autonomous music production for AI agents with MIDI generation, QC and provenance.
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.
AI music, video, image, and voice tools callable by agents with USDC payments via x402 on Base.
Deterministic music theory for agents: analyze, voice, reharmonize, conduct — computed, not guessed
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceExposes 16 music21 MIDI analysis and editing tools to AI agents, enabling them to read, edit, generate, and analyze MIDI files through natural language.MIT
- FlicenseNot gradedqualityDmaintenanceControls OpenUtau (vocal synthesis software) from Claude Desktop, enabling project creation, editing, and live note manipulation via a bridge plugin.1-
- AlicenseBqualityDmaintenanceEnables coding agents to compose, tune, render, mix, and audit native VOCALOID3/4 projects from scratch, acting as a production bridge between intent and finished song.2214MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to create and edit Strudel music code, render offline WAV audio, and obtain structured hearing reports with waveform, spectrogram, BPM, and onset analysis.AGPL 3.0