Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Recently observed → Live
Added "apply_reverb", "denoise_audio", "export_midi" and 4 more; removed "check_separation_status", "process_audio", "submit_separation" and 1 more; changed the definition of "check_task_status" and "extract_vocals" (10 tools before, 13 now)
Check the status of atasktask.startedJustbypassprocess_audio.task_id. It auto-detects all generated tracks, MIDI, and chords.
{"properties":{"task_idkwargs":{"title":"Task Idkwargs","type":"string"},"task_typetask_id":{"default":"4stems","title":"TaskTypeId","type":"string"}},"required":["task_id","kwargs"],"title":"check_task_statusArguments","type":"object"}
Extractthe vocals from a song — a convenient shortcut for process_audio with task_type='2stems'. Returns two stems: the isolated vocalsVocals andthe instrumental. Ideal for a cappella, karaoke, covers or vocal practice. Args: source_key: The source_key returned by upload_audio or get_upload_url. format: Output format, 'mp3'Instrumental (default) or2'wav'.Stems).
⟨5 unchanged words⟩ ":"Format","type":"string"},"kwargs":{"title":"kwargs","type":"string"},"source_key":{"title":"Source Key","type":"string"}},"required":["source_key","kwargs"],"title":"extract_vocalsArguments","type":"object"}
AI Sound Reverb.
AI Sound Denoise. mode='music' or 'speech'.
AI MIDI Export.
AI Chord Recognition.
Quick Splitter: isolate a single instrument (e.g., guitar, piano).
Split into 4 stems: vocals, drums, bass, other.
Split into 6 stems: vocals, guitar, bass, drums, piano, other.
[Deprecated] Use check_task_status instead.
Process an uploaded audio file. Main entry point for all SonicAura features.
[Deprecated] Use process_audio instead.
Upload a small audio file (under 1MB) via base64 encoding.
Live → Recently observed
Added "extract_vocals" (9 tools before, 10 now)
Extract the vocals from a song — a convenient shortcut for process_audio with task_type='2stems'. Returns two stems: the isolated vocals and the instrumental. Ideal for a cappella, karaoke, covers or vocal practice. Args: source_key: The source_key returned by upload_audio or get_upload_url. format: Output format, 'mp3' (default) or 'wav'.
Certificate recorded, valid to 2026-12-06
Authorization not required
Unknown → Live
First tool surface recorded: 9 tools (server version 1.30.0)
https://api.sonicaurastudio.com/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 9 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed