# stems-mcp

> stems-mcp — sandraschi-stems-mcp. Use this tool when you need to separate audio tracks into individual components, such as vocals, drums, bass, and other instruments, from any audio file. It solves the problem of isolating specific sounds from mixed audio, providing outputs of separated audio tracks. The tool takes an audio file as input and outputs the separated tracks, making it ideal for music production, remixing, and audio editing tasks.

Canonical page: https://skillsregistry.net/skills/sandraschi-stems-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sandraschi-stems-mcp

## Description

ONNX Runtime stem separation (Demucs HTDemucs). Separate vocals, drums, bass, other from any audio file. Model auto-downloads from HuggingFace. Companion to mixx-dj-mcp.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/sandraschi/stems-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sandraschi-stems-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sandraschi-stems-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sandraschi-stems-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt