About Audio Analysis MCP
Audio Analysis MCP is an MCP server in the Blockchain category: python MCP server with audio-analysis tools — import, Demucs stem separation, spectrum, transcription, note isolation, and comparison — for AI-driven sound recreation.
Install
git clone https://github.com/uribrecher/audio-analysis-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (10)
amplitude_analyzePer-cluster ADSR analysis with cross-candidate consistency check (**not ready for production** — see `docs/TODO.md`)
Parameters not published.
audio_compareCompare target vs. synthesized audio (mel spectrogram distance, per-band energy)
Parameters not published.
audio_list_devicesList available audio input devices
Parameters not published.
audio_renderCapture audio from a system device (BlackHole, USB audio)
Parameters not published.
import_audioImport a local audio file, normalize to 44.1kHz 16-bit mono WAV
Parameters not published.
note_isolateIsolate a note from audio within a time-frequency box via STFT masking
Parameters not published.
note_transcribePolyphonic transcription via Basic Pitch — outputs MIDI + note events JSON
Parameters not published.
note_triageAnalyze transcription, select best candidate notes for isolation
Parameters not published.
spectrum_analyzeExtract mel spectrogram, spectral features, ADSR, and modulation
Parameters not published.
stem_separateSeparate audio into stems (vocals, drums, bass, other, guitar, piano) using Demucs
Parameters not published.
Ask AI
Ask AI about Audio Analysis MCP
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.