Audio Sonic MCP — Claude Code MCP server for music analysis
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.
MIT ★ 5 updated 2026-08-22
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:1.2.0What Audio Sonic MCP 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.
What it helps with
- measure a track’s BPM and detect tempo drift
- identify its key and section-level changes
- extract vibe tags and production characteristics
Example prompts for the agent
- 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.
How to install Audio Sonic MCP
Platform CLI
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:1.2.0Replace <…> with your own values
Platform CLI
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:1.2.0Replace <…> with your own values
Config file
{
"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
Config file
{
"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
Platform CLI
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:1.2.0Replace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Audio Sonic MCP
How do I install Audio Sonic MCP in Claude Code?
Run `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`. The command launches the server with Docker.
What does Audio Sonic MCP do?
It analyzes audio and returns tempo, key, vibe tags, and production measurements. YouTube URL analysis runs asynchronously.
What does Audio Sonic MCP need to run?
Its installation command uses Docker and the JOBS_ROOT and KEEP_JOB_FILES values. The optional full model stack is installed with pip install -e ".[clap]" and adds CLAP and Demucs.