Sonicaura Mcp

io.github.warmcodingv1.0.0Updated Oct 11, 2026

Remote MCP server for audio stem separation, denoise, and reverb.

VerifiedStreamable HTTPWeb executableMedia & Design

Overview

AI-generated overview

A remote MCP server that lets an assistant split audio into stems, remove noise, and add reverb presets.

What it does
SonicAura runs GPU-accelerated audio processing through a remote endpoint. Its tools list available task types, check service status and remaining credits, obtain a presigned upload URL or send small base64 uploads, submit a processing task, and poll that task until it finishes. Supported tasks are stem separation into 2, 4, or 6 stems, music denoise, aggressive speech denoise, and reverb with presets such as vocal booth, studio room, or concert hall.
When to use it
Useful when an assistant needs to prepare audio material: isolating vocals, drums, bass, guitar, or piano from a track, producing an instrumental, cleaning up noisy music or voice recordings, or adding spatial reverb to a vocal. It fits music, podcast, and voiceover workflows where the audio can be sent to a hosted service.
Requirements
A remote Streamable HTTP endpoint at added to the MCP client configuration. Authentication is OAuth 2.0. Network access is required, and processing consumes service credits that the tools can report.
Before you install
Audio files are uploaded to a third-party hosted service, so avoid sending confidential or unreleased material unless that is acceptable. Processing consumes credits, and larger files are sent through a presigned upload URL. Tasks are submitted and polled asynchronously, so results depend on the remote service being available.

Installation

In SourceWeft

  1. Open Sonicaura Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "sonicaura-mcp": {
      "type": "http",
      "url": "https://api.sonicaurastudio.com/mcp"
    }
  }
}

README

[SonicAura Logo]

[Smithery]

sonicaura-mcp

Remote MCP server for audio stem separation, denoise, and reverb.

What it does

SonicAura processes audio using GPU-accelerated AI:

  • Stem separation — split a track into 2, 4, or 6 stems
    • 2stems: vocals + no_vocals
    • 4stems: vocals + drums + bass + other
    • 6stems: vocals + guitar + bass + drums + piano + other
  • Denoise
    • music_denoise: remove noise from music while keeping the instruments and vocals intact
    • denoise: aggressive speech cleanup for podcasts / interviews / voiceovers
  • Reverb — add spatial reverb with presets: vocal_booth, studio_room, bathroom, concert_hall, church

Endpoint

https://api.sonicaurastudio.com/mcp

Transport: http (Streamable HTTP) Auth: OAuth 2.0

Tools

ToolDescription
list_audio_toolsList available task types and metadata
check_service_statusConfirm service availability and credits
get_upload_urlPresigned URL for files larger than 1 MB
upload_audioBase64 upload for files under 1 MB
process_audioSubmit a task (music_denoise | denoise | reverb | 2stems | 4stems | 6stems)
check_task_statusPoll a task
get_my_creditsCheck remaining credits

Usage

Add the server to your MCP client config:

{  "mcpServers": {    "audio-process": {      "type": "http",      "url": "https://api.sonicaurastudio.com/mcp"    }  }}

Then ask your client things like:

  • "Extract the vocals from this song"
  • "Remove the vocals and keep the instrumental"
  • "Separate this song into 6 stems"
  • "Isolate the guitar track"
  • "Denoise this music but keep the background music"
  • "Clean up the noise in this voice recording"
  • "Add studio reverb to this vocal"

Credits

Processing uses credits. Get an account and credits at https://www.sonicaurastudio.com

License

MIT

Source: README.md at commit 38fba3b

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 11, 2026