# Audio Sonic MCP

Audio Sonic MCP is a Claude Code MCP server that analyzes music and returns tempo, key, vibe tags, and production traits. Ask it to inspect an audio file or a YouTube URL.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5 repo stars
- Author: ripunjay-kashyap
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ripunjay-kashyap/audio-sonic-mcp
- Updated: 2026-08-22
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/audio-sonic-mcp

## What it does

Audio Sonic MCP analyzes audio and returns structured track details: BPM, musical key, mood and genre tags, plus vocal presence, stereo width, and frequency peaks. For YouTube URLs, the MCP server runs the analysis asynchronously so the client model is not held up by processing.

The full model stack adds a CLAP embedding and Demucs stem separation. The lighter setup uses HPSS and standard librosa features, leaving out `vibe_tags` and CLAP vectors. The supplied launch command requires Docker and passes `JOBS_ROOT` and `KEEP_JOB_FILES` to the container.

## Requirements
- Needs: Docker
- Environment variables: `JOBS_ROOT`, `KEEP_JOB_FILES` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env JOBS_ROOT=<JOBS_ROOT> --env KEEP_JOB_FILES=<KEEP_JOB_FILES> --transport stdio audio-sonic-mcp -- docker run -i --rm -e JOBS_ROOT -e KEEP_JOB_FILES ghcr.io/ripunjay-kashyap/audio-sonic-mcp:1.2.0
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add audio-sonic-mcp --env JOBS_ROOT=<JOBS_ROOT> --env KEEP_JOB_FILES=<KEEP_JOB_FILES> -- docker run -i --rm -e JOBS_ROOT -e KEEP_JOB_FILES ghcr.io/ripunjay-kashyap/audio-sonic-mcp:1.2.0
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "audio-sonic-mcp": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "JOBS_ROOT",
                "-e",
                "KEEP_JOB_FILES",
                "ghcr.io/ripunjay-kashyap/audio-sonic-mcp:1.2.0"
            ],
            "env": {
                "JOBS_ROOT": "<JOBS_ROOT>",
                "KEEP_JOB_FILES": "<KEEP_JOB_FILES>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "audio-sonic-mcp": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "JOBS_ROOT",
                "-e",
                "KEEP_JOB_FILES",
                "ghcr.io/ripunjay-kashyap/audio-sonic-mcp:1.2.0"
            ],
            "env": {
                "JOBS_ROOT": "<JOBS_ROOT>",
                "KEEP_JOB_FILES": "<KEEP_JOB_FILES>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e JOBS_ROOT=<JOBS_ROOT> -e KEEP_JOB_FILES=<KEEP_JOB_FILES> audio-sonic-mcp docker run -i --rm -e JOBS_ROOT -e KEEP_JOB_FILES ghcr.io/ripunjay-kashyap/audio-sonic-mcp:1.2.0
```
Replace <…> with your own values

## When to use it
- measure a track’s BPM and detect tempo drift
- identify its key and section-level changes
- extract vibe tags and production characteristics

## Example prompts
- Analyze this audio file and return its BPM, key, and vibe tags.
- Inspect this YouTube URL and summarize the production profile.
- Compare the tempo and key of these tracks.

## Similar
- [cartesia-sonic](https://affpapa.org/en/nevibecode/skills/cartesia-sonic.md) — skill · 135 installs
- [audio-design](https://affpapa.org/en/nevibecode/skills/audio-design.md) — skill · 14200 installs
- [godot-audio](https://affpapa.org/en/nevibecode/skills/godot-audio.md) — skill · 12200 installs
- [optimize-audio](https://affpapa.org/en/nevibecode/skills/optimize-audio.md) — skill · 7100 installs
- [qianwen-audio-tts](https://affpapa.org/en/nevibecode/skills/qianwen-audio-tts.md) — skill · 6200 installs
- [audio-setup-mixers](https://affpapa.org/en/nevibecode/skills/audio-setup-mixers.md) — skill · 4900 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
