How do I use Tonn MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Tonn MCP Server Master this track at -14 LUFS" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Tonn MCP Server

MCP (Model Context Protocol) server for the RoEx Tonn API — AI-powered audio mixing, mastering, and analysis.

This server exposes Tonn's audio processing capabilities as MCP tools, enabling AI assistants like Claude to mix, master, and analyse audio directly in conversation.

Tools

Tool	Description	Credits
`get_account_status`	View plan, credit balance, and recent tasks	Free
`get_upload_url`	Get a signed URL for uploading audio files	Free
`analyse_mix`	Analyse a mix or master for loudness, frequency balance, stereo width, and more	Charged
`master_track`	Master a track with configurable loudness and style (preview or final)	Preview free, final charged
`get_job_status`	Check the status of a long-running processing job	Free

Related MCP server: reaper-reapy-mcp

Authentication

This server uses OAuth 2.0 with the Tonn Portal as the Authorization Server. Users authenticate through their existing Tonn account — no API key pasting required.

The server implements RFC 9728 (Protected Resource Metadata) for automatic AS discovery.

Deployment

Cloud Run

gcloud run deploy tonn-mcp \
    --source . \
    --region europe-west1 \
    --allow-unauthenticated \
    --set-env-vars "TONN_MCP_PORTAL_URL=https://tonn-portal.roexaudio.com,TONN_MCP_API_URL=https://tonn.roexaudio.com,TONN_MCP_SERVER_URL=https://mcp.roexaudio.com"

Local development

pip install -e .
TONN_MCP_PORTAL_URL=http://localhost:5000 TONN_MCP_API_URL=https://tonn.roexaudio.com TONN_MCP_SERVER_URL=http://localhost:8080 uvicorn tonn_mcp.server:app --port 8080 --reload

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

mcp-producerOAuth
io.github.AceDataCloud
MCP server for Producer/Riffusion AI music generation
Audio Processing AI & Machine Learning
22
Prologue AIOAuth
ai.prologue
Direct AI video, image, music and storyboard production from any MCP client.
AI & Machine Learning Image & Video Processing Audio Processing
1
sonicaura-mcp BOAuth
io.github.warmcoding
Remote MCP server for audio stem separation, denoise, and reverb.
AI & Machine Learning Audio Processing
101
mozonicOAuth
com.mozonic
AI mixing and mastering: analyze your mixes, run DSP autofix, render stems, and master tracks.
Audio Processing Multimedia Processing AI & Machine Learning
1

Related MCP Servers

ReaperMCP
Audio Processing Multimedia Processing
xDarkzx
A
license
B
quality
A
maintenance
Connects AI assistants to REAPER for music production, enabling full control over tracks, MIDI, mixing, mastering, and audio analysis through 153 tools across 24 modules.
Updated 7 days ago (2026-10-14 03:48 UTC)
174
93
Apache 2.0
reaper-reapy-mcp
Audio Processing Multimedia Processing
wegitor
A
license
C
quality
B
maintenance
Enables AI assistants to control REAPER DAW via the Model Context Protocol, including track, FX, MIDI, and audio operations.
Updated 3 months ago (2026-07-07 19:14 UTC)
47
31 PyPI
87
MIT
reaper-mcp
Audio Processing Multimedia Processing
TwelveTake-Studios
A
license
C
quality
A
maintenance
A comprehensive MCP server that enables AI assistants to control REAPER DAW for mixing, mastering, MIDI composition, and full music production workflows with 130 tools.
Updated 21 days ago (2026-09-29 20:07 UTC)
179
1,283 PyPI
73
MIT
AI Sound MCP Server
Audio Processing Multimedia Processing Speech Processing
tjameswilliams
F
license
Not graded
quality
D
maintenance
Enables AI assistants to programmatically edit, analyze, and export audio projects through MCP tools, including multi-track editing, effects, transcription, and semantic search.
Updated 7 months ago (2026-03-29 22:42 UTC)
1
-