Skip to main content
Glama
Audionaut MCP Server

Audionaut MCP Server

Separate stems

separate_stems

Splits a clip into Drums/Bass/Other/Vocals tracks with the Demucs (htdemucs) source separator, aligned with the source clip. Slow: minutes for a full song, CPU only; reports progress in 5% steps when the call carries a progressToken.

Instructions

Splits a clip into Drums/Bass/Other/Vocals tracks with the Demucs (htdemucs) source separator, aligned with the source clip. Slow: minutes for a full song, CPU only; reports progress in 5% steps when the call carries a progressToken. Needs the model weights, which the Audionaut app downloads once (Settings > Separation); fails with model_missing until then, and with demucs_unavailable in builds without Demucs.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project": "<project>"
    },
    "name": "separate_stems"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNoPlaylist item id (default: the track's first clip)
taskNoName of the task this edit is part of, e.g. "remove speech pauses". In the open app, all edits with the same task name become one undo step: keep the name for every call of the task and change it when the next task starts. Without a task name, all edits of this session share one step
trackNoTrack id (default 0; imported audio lands on a new track)
projectYesPath to the .audium project package (absolute paths recommended)
threadsNoParallel segments (default: physical cores)
mute_sourceNoMute the source track's channels (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.6.7
    • addedInput schema / properties / task
      Added value: +{
      +  "description": "Name of the task this edit is part of, e.g. \"remove speech pauses\". In the open app, all edits with the same task name become one undo step: keep the name for every call of the task and change it when the next task starts. Without a task name, all edits of this session share one step",
      +  "maxLength": 80,
      +  "type": "string"
      +}
  2. First observedv0.2.0

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses runtime cost, CPU-only execution, progress reporting at 5% intervals, prerequisite model downloads, and specific failure modes (model_missing, demucs_unavailable). This is exactly the kind of context an agent needs before invoking a slow, dependency-sensitive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and output, followed by performance characteristics and dependency/failure details. Every sentence adds useful information and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, slow, dependency-sensitive tool with no annotations and no output schema, the description covers prerequisites, failure modes, progress behavior, and output stems well. It does not explain the return value or whether track identifiers are returned, which would be useful given the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters including clip, task, track, project, threads, and mute_source. The description adds little parameter-level meaning, aside from mentioning a progressToken that is not part of the input schema; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Splits a clip into Drums/Bass/Other/Vocals tracks' using a named separator (Demucs/htdemucs). It is clearly distinguishable from generic siblings like split or assemble because it describes source separation into named stems.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operational context for choosing this tool: it is slow (minutes per full song, CPU only) and requires downloaded model weights. It does not explicitly name an alternative sibling or state when-not-to-use, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.