Audio MCP Server

Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis. Exposed over MCP by the audio mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Point Claude at any audio file and it can tell you the key, tempo, dynamics, timbre, percussive character, stereo field, structural sections, and how the music evolves over time -- all from raw audio analysis, no images, no guessing, under 1% context window usage.

LLMs can see (vision) and read (text), but they can't hear. This project bridges that gap by running real audio analysis -- the same DSP techniques used in music information retrieval research -- and returning structured numerical data that Claude can reason about.

• Audio decoding — -- mp3, wav, flac, ogg, aac via Symphonia (pure Rust)
• Spectral analysis — -- centroid (brightness), bandwidth (richness), rolloff, flatness (tonality)
• Frequency band energy — -- RMS energy across 7 standard producer bands (sub-bass through brilliance) for mix diagnosis
• Spectral contrast — -- peak vs valley per band in dB, reveals clarity vs muddiness
• Dynamic range — -- crest factor, loudness range (95th-5th percentile), peak dBFS
• LUFS loudness — -- EBU R128 integrated loudness (ITU-R BS.1770-4 stereo channel summing), true peak (dBTP), loudness range (LRA), streaming platform targets. Validated to 0.0 dB of FabFilter Pro-L 2

Its toolset

Everything the assistant can do here goes through one of these:

• audio_info — Basic file info: duration, sample rate, sample count
• spectral_features — Brightness, richness, loudness, texture, timbre (MFCCs), frequency band energy, spectral contrast, dynamic range, LUFS loudness, stereo field
• harmonic_analysis — Key detection, pitch class distribution, tonnetz
• rhythm_analysis — Tempo (BPM), beat positions, tempo stability
• full_analysis — Everything above in one call, plus percussive character (HPSS), stereo field, and section boundaries. Recommended workflow: call without resolution
• compare — A/B two tracks -- analyses both and returns a compact diff table

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Audio's toolset — audio_info, spectral_features, harmonic_analysis and 3 more — is a fair guide to whether it matches your workflow. It is maintained by JuzzyDee; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the audio mcp server does with a few real requests.