Music Analysis

🚀 MCP Music Analysis

This repository contains a Model Context Provider (MCP) that uses MCP and librosa to analyze audio from local files, YouTube links, or audio links.

🚀 Quick Start

📦 Installation

# Clone the repository
git clone git@github.com:hugohow/mcp-music-analysis.git
cd mcp-music-analysis

# Create a virtual environment and install dependencies
uv venv
source .venv/bin/activate  # For Windows users: .venv\Scripts\activate
uv pip install -e .

Using Claude Desktop Version

Locate the Configuration File

The location of the configuration file varies depending on your operating system:

• macOS:

  ~/Library/Application\ Support/Claude/claude_desktop_config.json
  

• Windows:

  %APPDATA%\Claude\claude_desktop_config.json
  

• Linux:

  ~/.config/Claude/claude_desktop_config.json
  

Add the following content to your claude_desktop_config.json:

{
  "mcpServers": {
    "music-analysis": {
      "command": "uvx",
      "args": ["-n", "mcp-music-analysis"]
    }
  }
}

💻 Usage Examples

Basic Usage

Here are some example prompts you might use after the MCP is running. The MCP will understand these requests and execute the relevant tools:

Can you analyze the rhythm of /Users/hugohow-choong/Desktop/sample-6s.mp3?
Can you tell me the duration of https://download.samplelib.com/mp3/sample-15s.mp3?
Please calculate the MFCC of /path/to/another_audio.mp3.
What is the spectral centroid of the /path/to/music.wav file?
I want to know the pitch change time points of https://www.youtube.com/watch?v=8HFiFd9vx1c.

📋 To-Do List

• [x] Add URL to audio file download
• [x] Add YouTube to audio file conversion
• [ ] Try different Python environments (testing)
• [ ] Improve the installation guide
• [ ] Integrate Whisper for lyrics analysis
• [ ] Implement a Docker solution

📄 Author

Hugo How-Choong