Audio Analysis

Provides numerical fingerprints, spectrograms, pitch tracking, and other audio analyses through a single, token-efficient tool.

python

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "zachswift615-audio-analysis-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/audio-analysis-mcp",
        "python",
        "-m",
        "audio_analysis_mcp.server"
      ],
      "env": {
        "AUDIO_ANALYSIS_OUTPUT_DIR": "./audio-analysis-output"
      }
    }
  }
}

You can analyze audio files efficiently with the Audio Analysis MCP Server. It exposes a single tool that provides numerical fingerprints, visual outputs, pitch tracking, and more, all through a compact, token-friendly interface that you can call from any MCP client.

How to use

Use the MCP client to call the audio_analyze tool with the operation you need. You can request numerical data such as fingerprints, onsets, or formants, or generate visual outputs like spectrograms and waveforms. Visual results are saved to disk and the client can read the resulting image paths for display or further processing.

How to install

Prerequisites: ensure you have Python installed for the server module and the MCP runtime tool uv available on your system.

cd ~/projects/audio-analysis-mcp
~/.local/bin/uv sync

If you don’t have uv installed, run the following to install it:

curl -LsSf https://astral.sh/uv/install.sh | sh

Configuration and environment

Configure the MCP server in your project so you can run the audio analysis service. The following configuration runs the Python module that powers the server and sets an output directory for generated visuals.

{
  "mcpServers": {
    "audio_analysis": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/audio-analysis-mcp",
        "python",
        "-m",
        "audio_analysis_mcp.server"
      ],
      "env": {
        "AUDIO_ANALYSIS_OUTPUT_DIR": "./audio-analysis-output"
      }
    }
  }
}

Output behavior

Images and other visual outputs produced by the analysis are saved to the directory specified by AUDIO_ANALYSIS_OUTPUT_DIR. If you do not set this variable, a default directory will be used to store results.

Available tools

audio_analyze

Single tool that performs numerical and visual analyses on audio files, with operations including fingerprint, formants, spectrogram, waveform, waterfall, and pitch tracking.

Built by

VeilStrat

AI signals for GTM teams