Skip to main content
Glama
jhonsu01

SoundCraft MCP Server

by jhonsu01

Export SoundCraft sessions

export_session

Render one SoundCraft .scraft session or a folder to WAV, AIFF, FLAC, stems, MIDI, or editable sessions, with range, normalize, bit-depth, and peak/LUFS metering.

Instructions

Mix down one .scraft session, a list or every session in a folder: wav / aiff / flac mixdown (range, normalize, bit depth), stems (one file per track), MIDI, with peak and loudness (LUFS) of each mix.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoBounce up to this time (seconds; default the end of the last clip).
startNoBounce from this time (seconds; default the session start).
formatsNoOutputs: wav / aiff / flac (the mixdown), scraft (the editable SoundCraft session; its audio is copied into an "Audio Files" folder beside it), mid (the MIDI of the instrument tracks) and stems (one file per track, in a <name>_stems folder).
previewNoReturn a waveform picture of the first mix.
bit_depthNoBit depth of wav / aiff / flac / stems (flac: 16 or 24).24
input_dirNoEvery .scraft directly in this folder.
normalizeNoNormalize the mixdown to -0.1 dBFS peak.
overwriteNoReplace existing outputs.
input_pathNo
output_dirNoAbsolute output folder (default: next to the input; required for new files).
input_pathsNo
output_pathNoAbsolute output file for the first format (its extension must match).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare a non-destructive write (readOnlyHint=false, destructiveHint=false), lowering the burden. The description usefully adds output composition, e.g. stems land in a <name>_stems folder and scraft copies audio into an 'Audio Files' folder, plus normalize-to--0.1 dBFS and LUFS reporting. It does not address overwrite semantics, permissions, or failure behavior, so it adds moderate context but not rich disclosure.

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

Conciseness4/5

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

A single front-loaded sentence led by the verb 'Mix down', with parentheticals and slashes packing detail efficiently and no filler. It is slightly dense to parse, but every clause contributes information and nothing is redundant with the title.

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?

With 12 parameters, no required fields, and no output schema, the description still conveys the modes, the output formats, and the return information (peak and LUFS of each mix). It leaves the input_path vs input_paths vs input_dir selection and the first-format-only output_path behavior to the schema, but overall it is adequate for the tool's complexity.

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 83%, so the schema documents most parameters (range, bit depth, normalize, overwrite, output_dir). The description echoes the key ones (range, normalize, bit depth, stems) without adding syntax or constraints beyond the schema, so the baseline of 3 applies.

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

Purpose4/5

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

The description names a specific verb ('mix down') and resource ('one .scraft session') and enumerates the three input modes (single session, list, folder) plus the concrete output types (wav/aiff/flac, stems, MIDI, LUFS reporting). It is clearly an export/render operation distinct from edit_session or create_session. It stops short of explicitly contrasting with convert_audio, which is the nearest ambiguous sibling, so it earns a 4 rather than 5.

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

Usage Guidelines3/5

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

The three modes imply when each path parameter is relevant, but the description never states explicit when-to-use/when-not guidance or names an alternative (e.g., convert_audio for format-only changes). Usage is only inferable from the phrasing, matching the 'implied usage' level.

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