Sonicaura MCP server
Commit Nov 1, 2026Enables AI clients to perform audio stem separation, noise reduction, chord recognition, and MIDI export using GPU-accelerated AI.
Also known as warmcoding/sonicaura-mcp
- Stars
- 0
- Tools
- 13
- Downloads, 30 days
- —
- Latest version
- 1.1.1
- Last commit
- Nov 1, 2026
- License
- MIT
What is Sonicaura MCP?
Sonicaura enables AI clients to perform audio stem separation, noise reduction, chord recognition, and MIDI export using GPU-accelerated AI. It exposes 13 tools, such as get_upload_url, extract_vocals, split_4stems.
Summary generated from the project's README
About Sonicaura MCP server
Processing audio stems and cleaning up sound files from inside an AI client is what sonicaura-mcp enables. This remote MCP server uses GPU-accelerated AI to provide specialized tools for musicians and audio engineers. It connects to a remote endpoint via HTTP and requires OAuth 2.0 authentication to function. Users can manage their processing by checking remaining credits or monitoring task status through specific tool calls.
Developers can use this server to perform complex tasks like splitting a track into 2, 4, or 6 stems using tools such as extract_vocals, split_4stems, or split_6stems. The server also includes a Quick Splitter to isolate specific instruments, a denoise_audio tool for cleaning speech or music, and an apply_reverb function with presets like vocal_booth or concert_hall. To handle large files that exceed LLM limits, the get_upload_url tool provides presigned URLs for direct uploads.
What you can do with it
- 1Isolate specific musical instrumentsAsk the AI to separate a single instrument from a full track for sampling or study.
Written from the project's README. Every use case is checked against a quote from it.
How to install Sonicaura MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Sonicaura MCP in Claude Code
$ claude mcp add --transport http sonicaura-mcp https://api.sonicaurastudio.com/mcpInstall Sonicaura MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"sonicaura-mcp": {
"url": "https://api.sonicaurastudio.com/mcp"
}
}
}Install Sonicaura MCP in VS Code
.vscode/mcp.json
{
"servers": {
"sonicaura-mcp": {
"type": "http",
"url": "https://api.sonicaurastudio.com/mcp"
}
}
}Install Sonicaura MCP in VS Code CLI
$ code --add-mcp '{"name":"sonicaura-mcp","type":"http","url":"https://api.sonicaurastudio.com/mcp"}'Install Sonicaura MCP in Codex
$ codex mcp add sonicaura-mcp --url https://api.sonicaurastudio.com/mcpInstall Sonicaura MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.sonicaura-mcp] url = "https://api.sonicaurastudio.com/mcp"
Install Sonicaura MCP in Gemini CLI
$ gemini mcp add -s user --transport http sonicaura-mcp https://api.sonicaurastudio.com/mcpInstall Sonicaura MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"sonicaura-mcp": {
"url": "https://api.sonicaurastudio.com/mcp",
"type": "http"
}
}
}Sonicaura MCP tools 13
Detected from the READMEget_upload_urlextract_vocalssplit_4stemssplit_6stemsextract_single_instrumentextract_chordsexport_mididenoise_audioapply_reverbcheck_task_statuslist_audio_toolsget_my_credits
Show all 13 toolsShow fewer tools
check_service_status
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablewarmcoding/sonicaura-mcp is public and reachablegithub.com/warmcoding/sonicaura-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-01github.com/warmcoding/sonicaura-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model13 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 839 msPass
README
View on GitHubSonicaura processes audio using GPU-accelerated AI. It exposes atomic, 1-to-1 semantic tools optimized for LLM reasoning.
Features
- Stem Separation — split a track into 2, 4, or 6 stems
- Quick Splitter — isolate any single instrument (guitar, piano, bass, drums)
- Chord Recognition — detect chord progressions from the track
- MIDI Export — convert isolated instruments into editable MIDI files
- Denoise — remove noise from music or aggressively clean up speech
- Reverb — add spatial reverb with presets: vocal_booth, studio_room, bathroom, concert_hall, church
Endpoint
- URL:
https://api.sonicaurastudio.com/mcp - Transport: http (Streamable HTTP)
- Auth: OAuth 2.0
Tools
| Tool | Description |
|---|---|
get_upload_url |
Get a presigned URL for large file uploads (bypasses LLM limits). |
extract_vocals |
2 stems: isolate Vocals and Instrumental (Karaoke). |
split_4stems |
4 stems: Vocals, Drums, Bass, Other. |
split_6stems |
6 stems: Vocals, Guitar, Piano, Bass, Drums, Other. |
extract_single_instrument |
Quick Splitter: isolate a specific instrument. |
extract_chords |
AI Chord Recognition: detect chord progression. |
export_midi |
AI MIDI Export: convert an isolated instrument into MIDI. |
denoise_audio |
Remove noise (use mode="music" or mode="speech"). |
apply_reverb |
Add spatial reverb. |
check_task_status |
Poll a task (requires only task_id). Auto-detects all outputs. |
list_audio_tools |
List available capabilities. |
get_my_credits |
Check remaining credits. |
check_service_status |
Check server health. |
Usage
Add the server to your MCP client config (Cursor, Claude Desktop, VS Code, etc.):
{ "mcpServers": { "sonicaura": { "type": "http", "url": "https://api.sonicaurastudio.com/mcp" } } }
Then ask your AI client things like:
- "Extract the vocals from this song"
- "Split this track into 6 stems"
- "Isolate the guitar track and export it as a MIDI file"
- "Detect the chords in this song"
- "Denoise this music but keep the background music"
- "Add studio reverb to this vocal"
Web UI
Prefer a visual interface? Use the same engine from the browser:
Credits & Pricing
Processing uses credits. Get an account and credits at sonicaurastudio.com
License
MIT
Sonicaura MCP questions
How do I add Sonicaura MCP to Claude Code?
Run claude mcp add --transport http sonicaura-mcp https://api.sonicaurastudio.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Sonicaura MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Sonicaura MCP provide?
It exposes 13 tools, including get_upload_url, extract_vocals, split_4stems, split_6stems, extract_single_instrument.
How can I upload large audio files?
You can use the get_upload_url tool to obtain a presigned URL, which allows you to bypass LLM file size limits.
What kind of reverb presets are available?
The server provides several spatial reverb presets including vocal_booth, studio_room, bathroom, concert_hall, and church.
Can I convert an instrument track to MIDI?
Yes, the export_midi tool allows you to convert an isolated instrument into an editable MIDI file.
How does the processing work?
Sonicaura processes audio using GPU-accelerated AI and exposes semantic tools optimized for LLM reasoning.