MCP 服务器

mcp-audio-analysis

MCP 用于分析本地音频文件。

数据与应用分析

Tools

load

Loads an audio file and returns the path to the audio time series Offset and duration are optional, in seconds. Be careful, you will never know the name of the song.

get_duration

Returns the total duration (in seconds) of the given audio time series.

tempo

Estimates the tempo (in BPM) of the given audio time series using librosa. Offset and duration are optional, in seconds.

chroma_cqt

Computes the chroma CQT of the given audio time series using librosa. The chroma CQT is a representation of the audio signal in terms of its chromatic content, which is useful for music analysis. The chroma CQT is computed using the following parameters: - path_audio_time_series_y: The path to the audio time series (CSV file). It's sometimes better to take harmonics only - hop_length: The number of samples between frames. - fmin: The minimum frequency of the chroma feature. - n_chroma: The number of chroma bins (default is 12). - n_octaves: The number of octaves to include in the chroma feature. The chroma CQT is saved to a CSV file with the following columns: - note: The note name (C, C#, D, etc.). - time: The time position of the note in seconds. - amplitude: The amplitude of the note at that time. The path to the CSV file is returned.

mfcc

Computes the MFCC of the given audio time series using librosa. The MFCC is a representation of the audio signal in terms of its spectral content, which is useful for music analysis. The MFCC is computed using the following parameters: - path_audio_time_series_y: The path to the audio time series (CSV file). It's sometimes better to take harmonics only

beat_track

Computes the beat track of the given audio time series using librosa. The beat track is a representation of the audio signal in terms of its rhythmic content, which is useful for music analysis. The beat track is computed using the following parameters: - hop_length: The number of samples between frames. - start_bpm: The initial estimate of the tempo (in BPM). - tightness: The tightness of the beat tracking (default is 100). - units: The units of the beat track (default is "frames"). It can be frames, samples, time.

download_from_url

Downloads a file from a given URL and returns the path to the downloaded file. Be careful, you will never know the name of the song.

download_from_youtube

Downloads a file from a given youtube URL and returns the path to the downloaded file. Be careful, you will never know the name of the song.

README

MCP 音乐分析

此仓库包含一个 模型上下文提供器 (MCP)，它使用 MCP 和 librosa 对本地、YouTube 链接或音频链接中的音频进行音频分析。

与 Claude Desktop 一起使用

安装

# 克隆仓库
git clone git@github.com:hugohow/mcp-music-analysis.git
cd mcp-music-analysis

# 创建虚拟环境并安装
uv venv
source .venv/bin/activate  # 在 Windows 上: .venv\Scripts\activate
uv pip install -e .

与 Claude Desktop 一起使用

找到配置文件

配置文件的位置取决于您的操作系统：

macOS:

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

Windows:

%APPDATA%\Claude\claude_desktop_config.json

Linux:

~/.config/Claude/claude_desktop_config.json

将以下内容添加到您的 claude_desktop_config.json：

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

示例提示

以下是一些示例提示，您可以在服务器运行后在对话或聊天环境中使用。 MCP 将理解这些请求并执行相关的工具：

你能分析一下 /Users/hugohow-choong/Desktop/sample-6s.mp3 的节拍吗？
你能告诉我 https://download.samplelib.com/mp3/sample-15s.mp3 的时长吗？
请计算此文件的 MFCC：/path/to/another_audio.mp3
/path/to/music.wav 的频谱质心值是多少？
我想知道 https://www.youtube.com/watch?v=8HFiFd9vx1c 的起始时间