melrose-mcp

melrose-mcp

An MCP server for generating and playing programmable music via Melrōse.

7
Stars
3
Forks
7
Watchers
1
Issues
melrose-mcp is a Model Context Protocol (MCP) server that enables users to compose and perform music using the Melrōse programming language. It facilitates communication between AI models and the Melrōse tool, allowing for dynamic manipulation of tempo, playback, and MIDI configuration. The project supports various tools for controlling musical expression and can be integrated into client applications such as Claude Desktop.

Key Features

MCP server implementation using Melrōse engine
Programmable music composition and playback
Adjustable tempo via API commands
Integration with MIDI devices and DAWs
Support for music commands from LLM-based clients
Custom tools for playback and device management
Configurable server for client integration
Real-time musical expression based on user or AI input
Example configuration for popular AI client environments
Documentation and support for extending music capabilities

Use Cases

Automated music composition and playback via API
Integrating music generation into conversational AI platforms
Dynamic tempo and playback control for music software
Programming musical expressions for live performance
Creating educational music programming environments
Enabling AI to produce music in specific styles or tempos
Real-time interaction with DAWs or hardware synthesizers
Interactive music demonstrations in client applications
Composing and testing algorithmic music sequences
Collaborative music creation between humans and language models

README

melrose-mcp

melrōse is a tool to create and play music by programming melodies. It uses a custom language to compose notes and create loops and tracks to play.

melrose-mcp is an MCP server (STDIO) that uses the packages from the melrōse tool.

installation

This mcp server requires the Go SDK for installation. To produce music, you need to setup a MIDI receiver such as a DAW or a hardware synthesizer.

go install github.com/emicklei/melrose-mcp@latest

tools

  • melrose_play
  • melrose_bpm
  • melrose_devices
  • melrose_change_output_device

session

change the tempo in melrose to a lower value

melrose_bmp request:

javascript
{
  `bpm`: `80`
}

llm response:

I've reduced the tempo to 80 beats per minute from the default of 120 BPM. This creates a more relaxed and slower pace for any musical expressions we play.

play a tune from Claude Debussy

llm response:

I'll create a small segment inspired by Claude Debussy's impressionist style using the Melrose language at our current tempo of 80 BPM.

melrose_play request:

javascript
{
  `expression`: `sequence('(F4 A4 D5) 4(F4 A4 D5) (G4 B4 E5) 4(G4 B4 E5) (A4 C5 F5) 4(A4 C5 F5) (G4 B4 E5) 4(G4 B4 E5) (F4 A4 D5) 8= 8(E4 G4 C5) 4(F4 A4 D5)')`
}

melrose_play response:

javascript
12.749963417s

configuration in your client

Below an example to configure it in Claude Desktop.

{
    "mcpServers": {
        "melrōse": {
          "command": "<YOUR DIRECTORY TO THE BINARY>/melrose-mcp",
          "args": []
        }
    }
}

example prompts

  • play the music sequence C D E
  • play the first bar of fur elise
  • play the famous tune from Mike Oldfield called Tubular Bells
  • play the notes of Frere Jacques
  • play the C# chord

To help your LLM understand the Melrōse language better, you can use this context.

Contributions

Fixes, suggestions, documentation improvements are all welcome. Fork this project and submit small Pull requests. Discuss larger ones in the Issues list. You can also sponsor Melrōse via Github Sponsors.

Software is licensed under MIT. © 2025 ernestmicklei.com

Star History

Star History Chart

Repository Owner

emicklei
emicklei

User

Repository Details

Language Go
Default Branch main
Size 162 KB
Contributors 1
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

Go
99.65%
Makefile
0.35%

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • Spotify MCP Server

    Spotify MCP Server

    A lightweight MCP server enabling AI assistants to control Spotify playback and manage playlists.

    Spotify MCP Server is a lightweight implementation of the Model Context Protocol that allows AI assistants, such as Cursor and Claude, to control Spotify playback and manage playlists. It provides a set of tools for searching music, managing playback state, handling playlists, and accessing user-specific track data. The server integrates seamlessly with productivity assistants and editors to facilitate contextual music control via standardized protocols. It includes authentication, Spotify API configuration, and detailed operations for reading and updating playback context.

    • 179
    • MCP
    • marcelmarais/spotify-mcp-server
  • Parallel Task MCP

    Parallel Task MCP

    Launch deep research or task groups for Parallel APIs via the Model Context Protocol.

    Parallel Task MCP provides a way to initiate and manage research or task groups through LLM clients using the Model Context Protocol. It enables seamless integration with Parallel’s APIs for flexible experimentation and production development. The tool supports both remote and local deployment, and offers connection capabilities for context-aware AI workflows.

    • 4
    • MCP
    • parallel-web/task-mcp
  • Enrichr MCP Server

    Enrichr MCP Server

    Gene set enrichment analysis server for LLMs via the Model Context Protocol

    Enrichr MCP Server provides gene set enrichment analysis using the Enrichr API, supporting all available gene set libraries. It is designed to integrate with LLM tools through the Model Context Protocol and returns only statistically significant results. The tool allows queries across multiple biological, disease, tissue, drug, and pathway gene set libraries, with customizable configuration for popular or specific libraries. Installation and integration is streamlined for platforms like Claude Desktop, Cursor, and VS Code.

    • 7
    • MCP
    • tianqitang1/enrichr-mcp-server
  • Driflyte MCP Server

    Driflyte MCP Server

    Bridging AI assistants with deep, topic-aware knowledge from web and code sources.

    Driflyte MCP Server acts as a bridge between AI-powered assistants and diverse, topic-aware content sources by exposing a Model Context Protocol (MCP) server. It enables retrieval-augmented generation workflows by crawling, indexing, and serving topic-specific documents from web pages and GitHub repositories. The system is extensible, with planned support for additional knowledge sources, and is designed for easy integration with popular AI tools such as ChatGPT, Claude, and VS Code.

    • 9
    • MCP
    • serkan-ozal/driflyte-mcp-server
  • Exa MCP Server

    Exa MCP Server

    Fast, efficient web and code context for AI coding assistants.

    Exa MCP Server provides a Model Context Protocol (MCP) server interface that connects AI assistants to Exa AI’s powerful search capabilities, including code, documentation, and web search. It enables coding agents to retrieve precise, token-efficient context from billions of sources such as GitHub, StackOverflow, and documentation sites, reducing hallucinations in coding agents. The platform supports integration with popular tools like Cursor, Claude, and VS Code through standardized MCP configuration, offering configurable access to various research and code-related tools via HTTP.

    • 3,224
    • MCP
    • exa-labs/exa-mcp-server
  • MaxMSP-MCP Server

    MaxMSP-MCP Server

    Bridge LLMs with Max patches via Model Context Protocol

    MaxMSP-MCP Server enables large language models to understand, explain, and generate Max patches by leveraging the Model Context Protocol. It connects LLM agents with MaxMSP environments, providing access to documentation and patch objects for detailed interaction. Installation includes both a Python server and Max environment integration, facilitating seamless Python-Max communication. The tool supports explaining patches, debugging, and synthesizer creation directly through LLM interfaces.

    • 106
    • MCP
    • tiianhk/MaxMSP-MCP-Server
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results