MCP Music Analysis

🚀 MCP Music Analysis

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

🚀 Quick Start

Usage with Claude Desktop

📦 Installation

Automatic Installation via Smithery

Automatically install Music Analysis for Claude Desktop through Smithery:

npx -y @smithery/cli install @hugohow/mcp-music-analysis --client claude

Manual Installation

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

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

Usage with Claude Desktop

Locate the Configuration File

The location of the configuration file varies depending on the 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 claude_desktop_config.json:

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

💻 Usage Examples

Example Prompts

Here are some example prompts that might be used when the MCP is running, demonstrating possible user queries:

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

📋 To-Do List

• [x] Add the function to download audio files from URLs
• [x] Add the conversion from YouTube to audio files
• [ ] Test multiple Python environments
• [ ] Improve the installation guide
• [ ] Integrate Whisper for lyrics analysis
• [ ] Implement a Docker solution

📄 Author

Hugo How-Choong

Badge