Audio Sonic MCP

🎵 Audio Sonic MCP

Turn any song into a structured "sonic signature" — extracting tempo, musical key, a 512-dimension CLAP vibe embedding, human-readable vibe tags, and a production profile — from a single local call.

Audio Sonic MCP runs entirely on your local machine (requiring no API keys, external servers, or cloud dependencies) and exposes two premium access points to the same underlying high-fidelity audio analysis engine:

---

🎹 Quick Taste: What You Get

1. Musician-Friendly CLI Summary (--summary mode)

🎵 SONIC SIGNATURE — my_demo.mp3  (3:24)

TEMPO 153.8 BPM (steady) KEY G Major · shifts to G Phrygian @0:30 (confidence 74%) VIBE aggressive · dark · driving · hip-hop · gritty

PRODUCTION Vocals forward Punch 0.62 (moderate) Stereo wide Low end ~55 Hz dominant

Overall confidence: 88% · analyzed in 0:28 (GPU-accelerated)

2. Comprehensive JSON (Returned by MCP and CLI by default)

{

"header": { "job_id": "sig_a3f9b2c1", "status": "success", "confidence_score": 0.88, "source_metadata": { "title": "Acoustic Vibe Demo", "duration_sec": 204, "source_type": "file" } }, "sonic_signature": { "bpm": 153.8, "bpm_engine": "madmom", "bpm_variable": false, "key": "G Major", "key_variable": true, "key_map": [ { "start_sec": 0.0, "end_sec": 30.0, "key": "G Major" }, { "start_sec": 30.0, "end_sec": 90.0, "key": "G Phrygian" } ], "mode_confidence": 0.74, "vibe_vector": [0.012, -0.034, "... 512 float dimensions ..."], "vibe_tags": ["aggressive", "dark", "driving", "hip-hop", "gritty"], "production_profile": { "vocal_presence": "forward", "transient_punch": 0.62, "stereo_width": "wide", "dominant_freq_peaks_hz": { "harmonic": [55.0, 110.2], "percussive": [125.0, 250.1] } } }, "telemetry": { "inference_time_sec": 28.0 } }

---

⚡ Key Features

• 🥁 Tempo & Beat Tracking — Full BPM computation with variable-tempo drift detection and transient windowing.
• 🎹 Key & Harmonic Mapping — Computes structural musical key + mode, generating a detailed key_map tracking section-by-section modulations.
• 🌈 Vibe & Style Embeddings — Compiles a 512-dimensional CLAP embedding and human-readable style tags (covering energy, texture, mood, and genre) using zero-shot music vocab classification.
• 🎚️ Production Analytics — Measures vocal spatial presence, transient punch coefficients, stereo width, and dominant frequency peaks.
• 🤖 MCP-Native System — Fully exposes 4 standardized Model Context Protocol tools for instant integration into AI tools.
• 🪶 Robust Graceful Degradation — Automatically utilizes a CUDA GPU if present and falls back to CPU; gracefully degrades to HPSS and standard librosa feature arrays if heavy deep learning packages ([clap]) are omitted.
• 🔒 100% Offline & Private — All conversion, separation, and inference occur locally.

---

📦 Installation & Setup

System Prerequisites

Ensure you have Python 3.10+ and FFmpeg installed and accessible on your system PATH.

Installing FFmpeg:

• macOS: brew install ffmpeg
• Linux (Debian/Ubuntu): sudo apt update && sudo apt install -y ffmpeg
• Windows: Run winget install Gyan.FFmpeg via PowerShell (Administrator), or download manually from ffmpeg.org and add the bin directory to your system environment variables.

---

Step-by-Step Installation

1. Clone the Repository

   git clone https://github.com/ripunjay-kashyap/audio-sonic-mcp.git

cd audio-sonic-mcp

1. Initialize Virtual Environment

   python -m venv .venv

Activate on macOS/Linux:

source .venv/bin/activate

Activate on Windows (PowerShell):

.venv\Scripts\activate

1. Install Dependencies Choose between the lightweight core engine or the full high-fidelity ML suite:

• Option A: Full High-Fidelity ML Suite (Recommended) Includes demixing stems (Demucs) and zero-shot vibe vectors (CLAP). Requires ~4 GB disk space. bash pip install -e ".[clap]"
• Option B: Core Lightweight Pipeline Uses standard digital signal processing (HPSS/librosa). Rapid install and minimal footprint. bash pip install -e .

[!NOTE]

The optional [clap] stack installs torch, torchaudio, transformers, and demucs. Without these, the server automatically switches to light fallbacks (HPSS instead of Demucs, standard feature matrices instead of CLAP vectors, and leaves out vibe_tags).

---

🤖 MCP Client Configuration Guide

Audio Sonic MCP registers itself as a standard package script. This enables you to run it using the global executable name (audio-sonic-mcp) directly from your virtual environment's bin folder, or run the script file manually.

1. Claude Desktop Setup

Open your Claude configuration file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

Add the server to your mcpServers object:

{

"mcpServers": { "audio-sonic-mcp": { "command": "C:\\path\\to\\audio-sonic-mcp\\.venv\\Scripts\\audio-sonic-mcp.exe", "args": [], "env": { "JOBS_ROOT": "C:\\path\\to\\audio-sonic-mcp\\jobs" } } } }

[!IMPORTANT]

Windows Users: Always use double backslashes (\\) in JSON configuration paths. Point the executable directly to the .exe inside your .venv\Scripts\ directory.

---

2. Cursor IDE Integration

To integrate Audio Sonic MCP into Cursor's AI pane:

1. Navigate to Settings ➔ Features ➔ MCP.
2. Click + Add New MCP Server.
3. Fill in the parameters:

• Name: audio-sonic-mcp
• Type: command
• Command: /path/to/audio-sonic-mcp/.venv/bin/audio-sonic-mcp (use .exe extension on Windows)

---

3. Windsurf Integration

Open your Windsurf MCP configurations file (typically found at ~/.codeium/windsurf/mcp_config.json) and append the configuration:

{

"mcpServers": { "audio-sonic-mcp": { "command": "/path/to/audio-sonic-mcp/.venv/bin/python", "args": ["/path/to/audio-sonic-mcp/server.py"], "env": { "JOBS_ROOT": "/path/to/audio-sonic-mcp/jobs" } } } }

---

4. Cline (VS Code Extension) Setup

Open Cline's MCP setting file (usually located at %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json or equivalent platform storage) and add:

{

"mcpServers": { "audio-sonic-mcp": { "command": "/path/to/audio-sonic-mcp/.venv/bin/audio-sonic-mcp", "args": [], "env": { "JOBS_ROOT": "/path/to/audio-sonic-mcp/jobs" } } } }

---

🤖 Interaction Flow for AI Agents & LLMs

LLMs automatically learn how to use this server by reading its exposed tool definitions. Because audio stem separation and CLAP embeddings are computationally demanding, Audio Sonic MCP uses an Asynchronous Fire-and-Forget Job Pattern.

Automated LLM Workflow

  [User Prompts LLM]

│ ▼

1. Submit URL ──────────────► [Tool: get_sonic_signature] │ (Returns Job ID instantly) ▼
2. Notify User ◄───────────── [LLM acknowledges job is queued] │ ├───► 3. Wait 10-15s (Or proceed with other tasks) │ ▼
3. Check Progress ──────────► [Tool: get_job_status] │ (Checks status: running/success/error) ▼
4. Present Signature ◄─────── [LLM formats rich output for user]

Natural Prompts to Try

• *"Check the health of my audio-sonic-mcp server to make sure all ML components are ready."*
• *"Submit this YouTube track for sonic analysis: https://www.youtube.com/watch?v=XXXXXX."*
• *"Check the progress of my sonic signature job sig_a1b2c3d4 and summarize the BPM, production width, and vibe once complete."*

---

🎚️ CLI Usage (Local Files)

For musicians, engineers, and producers working directly in the terminal, you can analyze a full-length local file directly without running any background servers:

# Get a visual, musician-friendly sonic signature digest (recommended)

python analyze_file.py "my_demo.wav" --summary

Print full raw JSON directly to the stdout stream

python analyze_file.py "my_demo.wav"

Dump JSON payload to a file while keeping the stdout clean

python analyze_file.py "my_demo.wav" > signature.json

CLI Command Options Reference

Supported File Formats: wav, mp3, flac, ogg, m4a, aac.

---

🔧 Environment Variables Reference

Configure environment options by declaring these variables in your active terminal session, container environment, or the env block of your MCP configuration file:

---

🐳 Docker / Podman Execution

If you prefer to avoid setting up local Python libraries, running via containers encapsulates FFmpeg, yt-dlp, and the core Python dependencies (CPU-based pipeline):

# Build the container image

doc