MCP ExplorerExplorer

Musescore Mcp

@JordanSucheron 10 months ago
3 MIT
FreeCommunity
AI Systems
An MCP server for MuseScore.

Overview

What is Musescore Mcp

musescore-mcp is an MCP server designed to integrate MuseScore with LLM clients like Claude Desktop, facilitating basic music composition through natural language interactions.

Use cases

Use cases include generating chord progressions for existing melodies, composing new melodies, and extending musical phrases while maintaining stylistic coherence.

How to use

To use musescore-mcp, first clone the repository and install the required dependencies. Then, install the musescore-mcp-plugin in your MuseScore plugins directory. Open MuseScore, load your desired score, and connect the plugin from the plugins menu to start interacting with the LLM.

Key features

Key features include the ability to connect to MuseScore, manipulate scores, add notes and rests, select and delete elements, create tuplets, undo changes, and move between staves.

Where to use

musescore-mcp can be used in music composition, education, and any context where natural language processing can enhance the music creation process.

Content

MuseScore MCP Server

This MCP (Model Context Protocol) server integrates MuseScore with LLM clients like Claude Desktop, enabling basic music composition through natural language.

Brief demo here: https://www.canva.com/design/DAGlHeR706g/4UcXvK23I1axWOfm6lSSxQ/edit

Features

The server allows an MCP-connected LLM to:

  • Connect to MuseScore and manipulate an open score
  • Add notes and rests
  • Select and delete
  • Create tuplets
  • Undo a change
  • Move from staff to staff

Limitations

  • Can not understand multiple voices within a staff or navigate between them

Requirements

  • Python 3.9+
  • MuseScore 3 or 4 installed
  • MCP Python SDK

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/musescore-mcp-server.git
    cd musescore-mcp-server
    
  2. Install dependencies, either in a venv or globally:

    pip install -r requirements.txt
    
  3. Install the musescore-mcp-plugin by copying it into your MuseScore plugins dir (on my mac this was ~/Documents/MuseScore4/plugins)

  4. Configure your LLM with the MCP server (server.py). If you are using Claude Desktop and a venv, this can be done by creating a claude_desktop_config file like so:

Usage

Prepare MuseScore

Open musescore and whatever score you want to use. Then, connect the musescore-mcp-plugin and launch it by selecting it from the plugins menu.

Example Queries

Once connected, you can ask Claude questions like:

  • "Help me come up with some possible chords for the melody in my score
  • Compose a simple melody and show me 4 ways to harmonize it
  • Extend the melody in measures 1-12 with 4 measures that match the style of this piece

Development

If you want to add features to the MuseScore plugin and test them, the testClient.html file in this repo may be a useful development tool - simply extend it to call whatever functions you add.

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers