This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Streamable MCP server for ComfyUI MelBandRoFormer audio source separation.
Tool | Description |
| Check ComfyUI backend status |
| List available MelBandRoFormer models |
| Submit audio file for separation |
| Get job status/results |
| Cancel a running job |
| List all stored artifacts |
| Download artifact by name |
Related MCP server: Tonn MCP Server
cd /home/tyrel/projects/audio-sep-mcp
AUDIOSEP_MCP_PORT=8769 python mcp_server.py # serves on http://localhost:8769/mcpNote: default port 8765 collides with other local MCP servers — the systemd service below overrides it to 8769.
python app.py # serves on :8767Both services are managed as systemd user units and start automatically (linger enabled):
systemctl --user status audio-sep-mcp.service audio-sep-gradio.service
systemctl --user restart audio-sep-mcp.service audio-sep-gradio.service
journalctl --user -u audio-sep-mcp.service -fUnit files: ~/.config/systemd/user/audio-sep-mcp.service, ~/.config/systemd/user/audio-sep-gradio.service.
Variable | Default | Description |
|
| ComfyUI backend URL |
|
| MCP server port (systemd service overrides to |
|
| Working directory |
|
| Workflow file |
|
| Artifact cleanup age |
wav, mp3, flac, ogg, aac, m4a, mp4, webm
Splits audio into vocals.wav and instruments.wav in ~/Documents/audio-sep-output/artifacts/<job_id>/.
Remote MCP server for audio stem separation, denoise, reverb, and MIDI export.
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
MCP server for Producer/Riffusion AI music generation
Free stem, vocal, noise, reverb and format tools. Train RVC voices; convert vocals and whole songs.
