Atlas / MCP servers / warmcoding / sonicaura-mcp

sonicaura-mcpSAFE

mcp/warmcoding/sonicaura-mcp

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

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
—
Transport
streamable-http
License
MIT
Stars
0
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Smithery

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

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.so

Read from source at commit 7d6e1fc5013fOBSERVED · 2026-10-12
02

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (2)

MEDIUMAuth / authz · mcp.remote_no_auth · CWE-287, CWE-862
streamable-http
Why it matters. a network transport with no auth environment variable found
Fix. require a token
LOWInventory / provenance · mcp.no_tools_extracted · CWE-1104
server.json
Why it matters. the tool list is enumerated at runtime by tools/list, not declared in source
Fix. the page says so rather than showing an empty table

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 7d6e1fc5013ffull audit observations/trust-audit/mcp-server/warmcoding__sonicaura-mcp.json · Report an issue / request a re-scan
03

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-127d6e1fc5013fSAFEB89first audit
04

Questions

What is the sonicaura-mcp MCP server?

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

Is sonicaura-mcp safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does sonicaura-mcp need?

No credential environment variables were found in its source, so it appears to need none.

How does sonicaura-mcp run?

It speaks streamable-http, so it runs as a service you connect to over the network.

How current is this page?

The grade is for one exact copy of the source (7d6e1fc5013f), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement