The mcp-svstudio server enables integration of Synthesizer V Studio with LLMs for creating and editing vocal tracks.
Key capabilities:
Get project information about the current Synthesizer V Studio project
List all tracks in the project
Retrieve notes from a specific track
Add new tracks to the project
Add notes to a track, specifying lyrics, pitch, duration, and start time
Edit existing notes, modifying lyrics, timing, and pitch
Hosts the repository for the MCP server code, allowing users to clone and install the integration.
Uses Lua scripts to handle communication between the MCP server and Synthesizer V Studio application.
Supports integration with Synthesizer V Studio on macOS, with specific installation paths and configuration requirements.
Provides the runtime environment for the MCP server, enabling communication between LLMs and Synthesizer V Studio.
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., "@mcp-svstudio add lyrics to this melody track"
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.
MCP server for Synthesizer V AI Vocal Studio, which allows LLMs to create/edit vocal tracks e.g. adding lyrics to the melody.
Node.js (tested with v22)
Synthesizer V Studio (tested with V2)
git clone https://github.com/ocadaruma/mcp-svstudio.git
Copy below two files to Synthesizer V Studio scripts folder (On MacOS with V2 Studio, it's ~/Library/Application Support/Dreamtonics/Synthesizer V Studio 2/scripts by default)
sv-scripts/StartMCPServerRequestHandler.lua
sv-scripts/StopMCPServerRequestHandler.lua
Run StartServerRequestHandler on Synthesizer V Studio
From Scripts menu > MCP > StartServerRequestHandler
⚠️ Please do this before configuring MCP client. Otherwise, you will get connection issue.
⚠️ Please run only one MCP server at a time.
Add below config to the MCP server config of your client. (e.g. On MacOS Claude Desktop, it's ~/Library/Application Support/Claude/claude_desktop_config.json by default)
{
"mcpServers": {
"SynthesizerVStudioMCP": {
"command": "/path/to/node",
"args": [
"/path/to/mcp-svstudio/dist/index.js"
]
}
}
}Related MCP server: SV1 Agent Bridge
Sing something (then "Add harmony track")
Create an EDM vocal track
Add lyrics to the existing track
Install dependencies:
npm installBuild the server:
npm run buildFor development with auto-rebuild:
npm run watchAdd one or more notes to a track
Inputs: trackId (required), notes (required).
Add a new track to the project
Inputs: name.
Edit one or more notes
Inputs: trackId (required), notes (required).
Get information about the current Synthesizer V Studio project
Inputs: no named parameters.
Get all notes in a specific track
Inputs: trackId (required).
List all tracks in the current project
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct purpose targeting specific resources and actions: adding notes, adding tracks, editing notes, getting project info, getting track notes, and listing tracks. There is no overlap or ambiguity between these operations.
All tool names follow a consistent verb_noun pattern (e.g., add_notes, add_track, edit_notes, get_project_info, get_track_notes, list_tracks). The naming is uniform and predictable throughout the set.
With 6 tools, the server is well-scoped for managing a Synthesizer V Studio project. Each tool earns its place by covering essential operations like project info, track management, and note handling without being overly sparse or bloated.
The tool set provides strong coverage for core project and track operations, including CRUD-like actions for notes and tracks. A minor gap exists in the lack of tools for deleting notes or tracks, which agents might need to work around, but the surface supports basic workflows effectively.
MCP server for Producer/Riffusion AI music generation
MCP server for Google Veo AI video generation
MCP Server for Slima - AI Writing IDE for Novel Authors with AI Beta Reader.
MCP server for AI dialogue using various LLM models via AceDataCloud
