Skip to main content
Glama

als_write

Destructive

Modify Ableton Live .als project files on disk using sidechain, configure, attribute, or restore operations, requiring explicit confirmation before writing changes.

Instructions

Edit a saved .als project file on disk. Requires confirm=True.

Supported operations: 'sidechain', 'configure', 'attribute', 'restore'.
The target file must not be the one Live currently holds: Live writes its own
memory over the file when it next saves, without a conflict warning, and the
edit is gone. Live running on a different set is fine.

Returns:
    Dictionary reporting write status, changes made, and verification report.

Note:
    ``sidechain`` is here for the set Live is not holding, someone else's project
    wired on disk. Measured across the 174-project corpus (docs/limits.md section 9):
    74 of 82 in the house/trance BPM window use sidechain compression, median 6
    wirings each. For
    the set on screen use ``lom_set`` and keep the read-back.

    ``configure`` fills a plugin's parameter strip, which no LOM call can do whatever
    the strip currently holds. Two parameters written into an instance whose strip
    held nothing came back on reopen with their real values, writable through
    ``lom_set`` with ``read_back: applied``. Live allocates 128 slots per instance and
    leaves them all in the file, so nothing is inserted. Three fields of an existing
    element are filled.

    ``attribute`` sets one attribute anywhere in the file, addressed by an
    ElementTree expression. An expression matching more than one element is refused
    unless ``index`` picks one, and ``index`` counts the matches of that expression
    rather than tracks in the project: ``.//MidiTrack/Name/EffectiveName`` does not
    see the audio tracks at all.

    Where the expression comes from: ``als_read`` with ``locate='tempo'`` or
    ``locate='track_names'`` answers with the expression, the attribute and the
    index for those fields, which are the ones usually edited on a file. For
    anything else the expression is built by hand, and ``confirm=False`` resolves
    it against the file first and reports what it selects, so a wrong one is
    caught before it writes rather than after.

    Choosing between the four: ``sidechain`` and ``configure`` for the two things
    the LOM cannot do at all, ``attribute`` for anything else in the file, and
    ``restore`` to undo any of them. For
    the set open in Live, none of these: use lom_set, set_parameter or set_mix
    and keep the read-back.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tapNoWhere the sidechain listens on the source track: 'pre' before that track's own effects and fader, 'post' after them. Used by 'sidechain' only.post
pathYesFilesystem path to the .als project to edit. A backup is written first and can be put back with the restore operation.
indexNoWhich match to edit when the expression selects more than one element, counted from 0. An ambiguous expression is refused rather than resolved to the first match, so this is how to disambiguate.
valueNoFor 'attribute', the new attribute value. For 'configure', the parameter strip assignment as '<index>=<name>; ...'.
backupNoPath to the backup file to put back. Required by the 'restore' operation and read by no other.
createNoTrue adds the attribute when the element does not already carry it. False refuses, which catches a misspelled attribute name instead of inventing a field Live will ignore.
deviceNoDevice index within the target track chain, counted from 0. Used by 'sidechain' and 'configure'.
confirmNoTrue carries the edit out. False changes nothing and reports what the call requires, which is how to check the arguments first.
attributeNoWhich attribute of the selected element to set. Live stores most numbers under 'Value'. Used by 'attribute' only.Value
operationYesWhat to do. 'sidechain' wires a compressor to a trigger track, 'configure' fills a plug-in parameter strip, 'attribute' sets one XML attribute anywhere in the file, 'restore' puts a backup back. Each one reads a different subset of the arguments below.
expressionNoElementTree path selecting the element to edit, e.g. './/MasterTrack/DeviceChain/Mixer/Tempo/Manual'. Used by 'attribute' only. Read the tree with als_read first.
source_trackNoName of the track the compressor should listen to, which is usually the kick. Used by 'sidechain' only.
target_trackNoName of the track carrying the device to edit, as it appears in Live. Used by 'sidechain' and 'configure'.
allow_live_runningNoTrue permits the edit while Live is running at all. The check behind it looks for a running Live process and cannot tell which set that process holds, so it is not a guard against editing the open one: only you know that. What matters is the file, not the process. Live open on a different set is harmless. Live holding this file overwrites the edit from memory when it next saves.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed16 schema fields changedv0.1.1
    • addedInput schema / properties / allow_live_running / description
      Added value: +"True permits the edit while Live is running at all. The check behind it looks for a running Live process and cannot tell which set that process holds, so it is not a guard against editing the open one: only you know that. What matters is the file, not the process. Live open on a different set is harmless. Live holding this file overwrites the edit from memory when it next saves."
    • addedInput schema / properties / attribute / description
      Added value: +"Which attribute of the selected element to set. Live stores most numbers under 'Value'. Used by 'attribute' only."
    • addedInput schema / properties / backup / description
      Added value: +"Path to the backup file to put back. Required by the 'restore' operation and read by no other."
    • addedInput schema / properties / confirm / description
      Added value: +"True carries the edit out. False changes nothing and reports what the call requires, which is how to check the arguments first."
    • addedInput schema / properties / create / description
      Added value: +"True adds the attribute when the element does not already carry it. False refuses, which catches a misspelled attribute name instead of inventing a field Live will ignore."
    • addedInput schema / properties / device / description
      Added value: +"Device index within the target track chain, counted from 0. Used by 'sidechain' and 'configure'."
    • addedInput schema / properties / expression / description
      Added value: +"ElementTree path selecting the element to edit, e.g. './/MasterTrack/DeviceChain/Mixer/Tempo/Manual'. Used by 'attribute' only. Read the tree with als_read first."
    • addedInput schema / properties / index / description
      Added value: +"Which match to edit when the expression selects more than one element, counted from 0. An ambiguous expression is refused rather than resolved to the first match, so this is how to disambiguate."
    • addedInput schema / properties / operation / description
      Added value: +"What to do. 'sidechain' wires a compressor to a trigger track, 'configure' fills a plug-in parameter strip, 'attribute' sets one XML attribute anywhere in the file, 'restore' puts a backup back. Each one reads a different subset of the arguments below."
    • addedInput schema / properties / operation / enum
      Added value: +[
      +  "sidechain",
      +  "configure",
      +  "attribute",
      +  "restore"
      +]
    • addedInput schema / properties / path / description
      Added value: +"Filesystem path to the .als project to edit. A backup is written first and can be put back with the restore operation."
    • addedInput schema / properties / source_track / description
      Added value: +"Name of the track the compressor should listen to, which is usually the kick. Used by 'sidechain' only."
    • addedInput schema / properties / tap / description
      Added value: +"Where the sidechain listens on the source track: 'pre' before that track's own effects and fader, 'post' after them. Used by 'sidechain' only."
    • addedInput schema / properties / tap / enum
      Added value: +[
      +  "pre",
      +  "post"
      +]
    • addedInput schema / properties / target_track / description
      Added value: +"Name of the track carrying the device to edit, as it appears in Live. Used by 'sidechain' and 'configure'."
    • addedInput schema / properties / value / description
      Added value: +"For 'attribute', the new attribute value. For 'configure', the parameter strip assignment as '<index>=<name>; ...'."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, the description warns that Live will overwrite edits from memory on next save, that confirm=False performs a dry run, that ambiguous expressions are refused, and that index counts expression matches rather than project tracks. It also discloses that a backup is written first. These are significant behavioral facts an agent needs before calling a file-mutating tool.

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

Conciseness3/5

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

The description is front-loaded with the core purpose and confirm requirement, and the paragraphs are structured by operation. However, it is quite long and includes tangential material such as the 174-project corpus statistics and the sidechain wiring median, which do not help an agent invoke the tool correctly. The 'use lom_set for the open set' guidance is also repeated, adding redundancy.

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

Completeness5/5

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

Given the tool's complexity, 14 parameters, and destructive nature, the description is remarkably complete: it covers the return shape, operation-specific behavior, dry-run semantics, backup/restore flow, expression sourcing, Live-process caveats, and escape hatches to sibling tools. An agent has enough context to call this tool safely and correctly.

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

Parameters4/5

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

The input schema already documents all 14 parameters with 100% coverage, so the baseline is 3. The description adds value beyond the schema by explaining which parameters each operation reads, clarifying that index counts match occurrences rather than tracks, and showing where expressions come from via als_read. This is useful semantic context, though some of it does overlap with the schema text.

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 opens with a specific verb and resource: 'Edit a saved .als project file on disk.' It then enumerates the four supported operations, making the tool's scope immediately clear. It also distinguishes itself from sibling tools by explicitly saying 'for the set open in Live, none of these: use lom_set, set_parameter or set_mix.'

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

Usage Guidelines5/5

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

The description gives explicit selection guidance: sidechain and configure for things LOM cannot do, attribute for anything else in the file, restore for undo, and als_read for generating expressions. It also clearly warns when not to use the tool: when Live holds the target file, use lom_set-family tools instead. This is model guidance for routing an agent to the right tool.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/romanstark/live-maestro'

If you have feedback or need assistance with the MCP directory API, please join our Discord server