Ableton Producer MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Ableton Producer MCP create a 4-bar house beat at 124 BPM with kick, bass, and hats"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Ableton Producer MCP
An MCP server that lets Claude (or any MCP client) produce music in Ableton Live: build tracks, write MIDI, load and tweak devices, arrange sections and draw real automation, all from a chat.
It is a fork of ahujasid/ableton-mcp (MIT) extended for full-track production work. The fork adds arrangement editing, device-parameter control and clip and arrangement automation.
What this fork adds
Area | Tools |
Automation | Read, write and clear clip envelopes (Session and Arrangement clips). Write real Arrangement track automation (filter sweeps, builds, fades) with |
Devices | Read and set any device parameter, including on the master track ( |
Arrangement | Copy Session clips to the timeline, list Arrangement clips, rename them, move the playhead, create locators. |
Editing | Clear notes, delete clips, create audio tracks, load audio files into clips. |
State |
|
Safety | Version handshake with the Remote Script, and an installer that puts the script in the folder Live actually scans. |
Related MCP server: ableton-mcp-extended
Requirements
Ableton Live 11 or 12. Developed on Live 12.
insert_deviceneeds Live 12.1.5 or newer.Python 3.10+
uv (
brew install uvon macOS)An MCP client: Claude Code, Claude Desktop, Cursor or similar.
Installation
1. Clone the repository
git clone https://github.com/kovtun-oleksii/ableton-producer-mcp.git2. Install the Remote Script into Live
The MCP server talks to Live through a MIDI Remote Script (a control surface) that runs inside Live. Install it with:
uv --directory /absolute/path/to/ableton-producer-mcp run ableton-mcp-install-scriptThe script is copied to <User Library>/Remote Scripts/AbletonMCP/, the folder Live 10.1.13+ scans for third-party control surfaces. Useful options:
Option | What it does |
| Show which Remote Scripts folders were found, then exit. |
| Install into an explicit folder. |
| Overwrite even if |
| Also copy into the old |
3. Enable the control surface in Live
Restart Live.
Open Settings → Link, Tempo & MIDI. In Live 11 this is Preferences → Link Tempo MIDI.
Under Control Surface, pick AbletonMCP.
Set Input and Output to None.
The script listens on localhost:9877.
4. Connect your MCP client
Claude Code
claude mcp add AbletonMCP -- uv --directory /absolute/path/to/ableton-producer-mcp run ableton-mcpClaude Desktop. Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"AbletonMCP": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/ableton-producer-mcp", "run", "ableton-mcp"]
}
}
}Cursor and other clients: use the same command, uv --directory /absolute/path/to/ableton-producer-mcp run ableton-mcp.
Run only one MCP client against Live at a time, because they share the same socket.
5. Check the connection
With Live open, ask your assistant "What's in my Live set?". It should call get_session_info and report the tempo and tracks.
You can also query the Remote Script directly, bypassing the MCP server. Run this from the repository folder:
python3 scripts/live_call.py get_script_infoThe reply should report Remote Script version 1.8.3. If the server warns about a version mismatch, run step 2 again and restart Live.
Updating
git -C /absolute/path/to/ableton-producer-mcp pullIf the Remote Script changed, run the installer from step 2 again. Then restart Live, or re-select AbletonMCP under Control Surface.
Tools
Each tool also takes an optional user_prompt argument.
Session and transport
get_session_info, get_remote_script_info, get_session_snapshot, set_tempo, start_playback, stop_playback, switch_to_arrangement_view, set_arrangement_time
Tracks
get_track_info, create_midi_track, create_audio_track, set_track_name
Clips and notes (Session view)
create_clip, add_notes_to_clip, get_clip_notes, clear_notes_from_clip, set_clip_name, delete_clip, fire_clip, stop_clip, create_audio_clip
Arrangement
duplicate_to_arrangement, get_arrangement_clips, set_arrangement_clip_name, create_locator
Devices and browser
get_device_parameters, set_device_parameter, insert_device, load_instrument_or_effect, load_drum_kit, get_browser_tree, get_browser_items_at_path
Automation
get_clip_automation, set_clip_automation, clear_clip_automation, set_arrangement_automation, clear_arrangement_automation
Feedback and dataset (opt-in, see Telemetry and data)
set_dataset_consent, submit_intent, rate_last_action, prefer_candidate, reject_last_action, record_audition
Units and conventions
Time is in beats (quarter notes). In 4/4, bar N starts at beat
(N − 1) × 4. Notes look like{"pitch": 60, "start_time": 0.0, "duration": 0.5, "velocity": 96}. Middle C is 60 (C3 in Live).Parameter values use each parameter's own
min..maxrange. Callget_device_parametersfirst to find the index, range and current display value.Indices shift when tracks or devices are added or removed. Look things up by name right before each change, especially if you are editing the set at the same time.
Automation
Clip envelopes: set_clip_automation writes a curve into one clip, with times relative to the clip start:
{"track_index": 2, "clip_index": 0, "device_index": 1, "parameter_index": 4,
"points": [{"time": 0, "value": 0.2}, {"time": 16, "value": 0.8}]}Points ramp linearly. Add "step": true to a point to hold its value until the next point, which gives a jump.
Arrangement automation: Live's API cannot create envelopes inside Arrangement clips. set_arrangement_automation works around this:
Each Arrangement clip in the curve's span is rebuilt in a spare Session slot, with the same notes plus the envelope.
The rebuilt clip is copied back onto the timeline.
Live converts the envelope into real track automation.
Times are absolute Arrangement beats. Things to know:
The track needs one empty Session slot and MIDI clips covering the span. Audio clips, and clips looped or trimmed in the Arrangement, are skipped and reported.
Rebuilding a clip can reset that span for other automated parameters on the same track. Put all curves for the same span into one call (or one plan job, see below), then read the values back.
Group tracks and audio tracks that monitor an input can't be automated through the API.
For batch jobs, scripts/arrangement_automation.py plan.json runs the same technique from the command line. The plan format is described at the top of the script.
Tips and limits
Session overrides Arrangement. After firing Session clips, press Back to Arrangement in Live or the timeline stays muted.
Read parameter values with the transport stopped. During playback, readings lag about one beat.
Loading a device arms the track. Loading a device or sample selects that track and arms it; disarm it afterwards.
get_session_snapshotcan be very large. Passinclude_notes=falseandinclude_params=falsewhen you only need the structure.Not possible through this server: deleting or muting tracks, moving devices within a chain, choosing a sidechain source ("Audio From"). Do these by hand in Live.
Configuration
Variable | Default | Used by |
|
| MCP server |
|
|
|
| unset | Kill switch: set any of them to |
| unset | Installer skips the copy unless |
Telemetry and data
A fresh clone sends nothing. Telemetry and dataset recording need credentials in MCP_Server/config.py. That file is not part of this repository and is ignored by git.
The feedback and dataset tools record only after the user explicitly agrees via set_dataset_consent. The kill-switch variables above override any consent.
Development
python3 -m unittest discover -s testsscripts/live_call.pysends one raw command to the Remote Script and prints the reply. Use it to smoke-test script changes in a running Live.scripts/live_names.pyholds name-based track and device helpers, setters that take display values (such as dB), and a peak meter.scripts/arrangement_automation.pywrites Arrangement automation from a JSON plan.MCP_Server/bundled_ableton_remote_script/AbletonMCP_init.pyis the Remote Script that ships with the package. After editing it, run the installer again and reload the control surface in Live.
Credits and license
MIT, see LICENSE. Based on ableton-mcp by Siddharth Ahuja. This is a third-party project and is not affiliated with or endorsed by Ableton.
Available Tools
43 toolsadd_notes_to_clipB
Add MIDI notes to a clip.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot containing the clip
notes: List of note dictionaries, each with pitch, start_time, duration, velocity, and mute
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: notes (required), clip_index (required), track_index (required), user_prompt. Returns: result
clear_arrangement_automationA
Flatten a parameter's Arrangement automation to a constant value over
[start_time, end_time) in beats (end_time < 0 means to the last Arrangement clip).
Live's API can't delete track automation, so the span covered by the MIDI clips
in range is overwritten with value (same mechanism and limits as
set_arrangement_automation). To remove a lane completely, delete it in Live.
Parameters:
track_index: Track to flatten
value: The constant to write (parameter units, e.g. its un-automated setting)
start_time, end_time: Arrangement beat range
user_prompt: The original user prompt that led to this tool call (for telemetry)
Target (what to automate):
target_type: "device" (a device parameter) or "mixer" (track mixer)
device_index, parameter_index: for "device"; discover them with get_device_parameters
mixer_name: for "mixer": "volume", "panning" or "send"
send_index: for mixer_name "send" Values are in the parameter's own units (the same min..max that get_device_parameters reports), and are clamped to that range.
Inputs: value (required), track_index (required), end_time, mixer_name, +6 more. Returns: result
clear_clip_automationA
Remove automation from one clip: a single parameter's envelope, or every envelope when all_parameters is True.
Parameters:
track_index, clip_index, clip_view: which clip (see get_clip_automation)
all_parameters: Clear every envelope in the clip instead of one target
user_prompt: The original user prompt that led to this tool call (for telemetry)
Target (what to automate):
target_type: "device" (a device parameter) or "mixer" (track mixer)
device_index, parameter_index: for "device"; discover them with get_device_parameters
mixer_name: for "mixer": "volume", "panning" or "send"
send_index: for mixer_name "send" Values are in the parameter's own units (the same min..max that get_device_parameters reports), and are clamped to that range.
Inputs: clip_index (required), track_index (required), clip_view, mixer_name, +6 more. Returns: result
clear_notes_from_clipA
Remove all MIDI notes from a Session clip.
Writes are additive (add_notes_to_clip only appends), so to truly modify a clip you clear it first, then add the new notes. Use this with get_clip_notes and add_notes_to_clip for a real read -> modify -> write loop: read the notes, edit the list, clear_notes_from_clip, then add_notes_to_clip the edited notes.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot containing the clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), user_prompt. Returns: result
create_audio_clipA
Create a new audio clip in an audio track's clip slot by importing a file.
Requires Ableton Live 12.0.5 or newer — the underlying ClipSlot.create_audio_clip Live API was introduced in 12.0.5 and is not available in earlier 12.0.x releases.
Parameters:
track_index: The index of the audio track to create the clip in
clip_index: The index of the clip slot to create the clip in
path: Absolute path to a supported audio file (e.g. a .wav). The target track must be an audio track and the clip slot must be empty.
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: path (required), clip_index (required), track_index (required), user_prompt. Returns: result
create_audio_trackA
Create a new audio track in the Ableton session.
Use this for recorded or imported audio (samples, stems, vocals). For MIDI instruments use create_midi_track instead.
Parameters:
index: The index to insert the track at (-1 = end of list)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: index, user_prompt. Returns: result
create_clipB
Create a new MIDI clip in the specified track and clip slot.
Parameters:
track_index: The index of the track to create the clip in
clip_index: The index of the clip slot to create the clip in
length: The length of the clip in beats (default: 4.0)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), length, user_prompt. Returns: result
create_locatorA
Create a named locator (cue point) in the Arrangement at a beat position.
If a locator already exists at that beat (within ~1e-3 tolerance) it is renamed instead of toggled off. Time is in beats from the start of the arrangement (e.g. 0.0 = start, 16.0 = bar 5 in 4/4).
Parameters:
name: The locator label (e.g. "Chorus", "Verse 1", "Drop")
time: Beat position where the locator should sit
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: name (required), time (required), user_prompt. Returns: result
create_midi_trackA
Create a new MIDI track in the Ableton session.
Parameters:
index: The index to insert the track at (-1 = end of list)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: index, user_prompt. Returns: result
delete_clipA
Delete the clip in the given clip slot, freeing it for reuse.
Use this before create_clip when you want to overwrite an existing clip (create_clip itself refuses to write into an occupied slot).
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot to clear
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), user_prompt. Returns: result
duplicate_to_arrangementA
Copy a Session-view clip into the Arrangement timeline.
Uses Live's track.duplicate_clip_to_arrangement() API (Live 11 / 12). The clip is placed at destination_time beats from the start of the arrangement on the same track it lives in.
Typical workflow:
create_clip / add_notes_to_clip to build a Session clip
Call duplicate_to_arrangement once per bar/section you need
Call switch_to_arrangement_view to confirm the result in Live
Parameters:
track_index: Index of the track that owns the Session clip
clip_index: Index of the clip slot in that track (Session view)
destination_time: Beat position in the arrangement to place the clip (e.g. 0.0 = start, 8.0 = bar 3 in 4/4)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), destination_time (required), user_prompt. Returns: result
fire_clipB
Start playing a clip.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot containing the clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), user_prompt. Returns: result
get_arrangement_clipsA
List all clips placed in the Arrangement timeline for a track.
Returns each clip's name, start_time, end_time, length, and type.
Parameters:
track_index: The index of the track to inspect
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: track_index (required), user_prompt. Returns: result
get_browser_items_at_pathA
Get browser items at a specific path in Ableton's browser.
Parameters:
path: Path in the format "category/folder/subfolder" where category is one of the available browser categories in Ableton
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: path (required), user_prompt. Returns: result
get_browser_treeC
Get a hierarchical tree of browser categories from Ableton.
Parameters:
category_type: Type of categories to get ('all', 'instruments', 'sounds', 'drums', 'audio_effects', 'midi_effects')
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt, category_type. Returns: result
get_clip_automationA
Read a clip's automation envelope for one parameter, sampled every resolution beats.
Parameters:
track_index: Track that owns the clip
clip_index: Session slot index (clip_view="session") or index into the track's Arrangement clips as listed by get_arrangement_clips (clip_view="arrangement")
clip_view: "session" or "arrangement"
resolution: Sampling step in beats (capped to at most 512 samples)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Target (what to automate):
target_type: "device" (a device parameter) or "mixer" (track mixer)
device_index, parameter_index: for "device"; discover them with get_device_parameters
mixer_name: for "mixer": "volume", "panning" or "send"
send_index: for mixer_name "send" Values are in the parameter's own units (the same min..max that get_device_parameters reports), and are clamped to that range.
Inputs: clip_index (required), track_index (required), clip_view, mixer_name, +6 more. Returns: result
get_clip_notesA
Read all MIDI notes from a Session-view clip.
Returns pitch, start_time, duration, velocity, mute (and extended fields when available).
Parameters:
track_index: Track that owns the clip
clip_index: Session clip slot index
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), user_prompt. Returns: result
get_device_parametersA
Read all parameters for a device on a track (name, value, min, max).
Parameters:
track_index: Track that owns the device (-1 = master track)
device_index: Index into the track's device chain
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: track_index (required), device_index (required), user_prompt. Returns: result
get_remote_script_infoA
Report Ableton Remote Script version and capabilities (handshake).
Use this to verify the Live-side bridge matches this MCP server package.
Inputs: user_prompt. Returns: result
get_session_infoB
Get detailed information about the current Ableton session
Parameters:
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt. Returns: result
get_session_snapshotA
Capture a full project state snapshot for trajectory recording.
Includes session metadata, every track (mixer, devices, session clips, arrangement clips), optional MIDI notes, and optional device parameters. Used to version musical state S_t → S_{t+1}.
Parameters:
include_notes: Include MIDI note arrays in clips (default True)
include_params: Include device parameter values (default True)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt, include_notes, include_params. Returns: result
get_track_infoC
Get detailed information about a specific track in Ableton.
Parameters:
track_index: The index of the track to get information about
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: track_index (required), user_prompt. Returns: result
insert_deviceA
Insert a native Live device (e.g. "Utility", "Saturator", "Limiter", "EQ Eight") by name at a position in a track's device chain, without the browser. Works on the master track, where browser loads land on whichever track is selected. Needs Live 12.1.5+ and Remote Script 1.8.3+.
Parameters:
track_index: Track to insert into (-1 = master track)
device_name: Native device name as shown in Live's browser
target_index: Chain position (0 = first); -1 appends at the end
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: device_name (required), track_index (required), user_prompt, target_index. Returns: result
load_drum_kitB
Load a drum rack and then load a specific drum kit into it.
Parameters:
track_index: The index of the track to load on
rack_uri: The URI of the drum rack to load (e.g., 'Drums/Drum Rack')
kit_path: Path to the drum kit inside the browser (e.g., 'drums/acoustic/kit1')
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: kit_path (required), rack_uri (required), track_index (required), user_prompt. Returns: result
load_instrument_or_effectB
Load an instrument or effect onto a track using its URI.
Parameters:
track_index: The index of the track to load the instrument on (-1 = master track, for audio effects)
uri: The URI of the instrument or effect to load (e.g., 'query:Synths#Instrument%20Rack:Bass:FileId_5116')
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: uri (required), track_index (required), user_prompt. Returns: result
prefer_candidateA
Record a pairwise preference between two candidate actions or auditions.
winner should be 'a', 'b', or an explicit candidate id matching A or B.
Requires telemetry consent.
Parameters:
candidate_a: Id / URI / label for option A
candidate_b: Id / URI / label for option B
winner: 'a', 'b', or the winning id
reason: Optional reason ("C has the right attack")
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: winner (required), candidate_a (required), candidate_b (required), reason, +1 more. Returns: result
rate_last_actionA
Rate the most recent recorded action (or the track after an edit).
Ratings: better | same | worse | keep | reject | thumbs_up | thumbs_down Optional tags (comma-separated): groove, harmony, melody, sound, arrangement, energy, mix, emotion
Requires telemetry consent.
Parameters:
rating: Preference label
tags: Comma-separated aspect tags
note: Optional free-text reason
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: rating (required), note, tags, user_prompt. Returns: result
record_auditionA
Log a browser/preset/sample audition (keep or reject) for preference learning.
Call once per candidate auditioned. Does not load the device — use load_instrument_or_effect when kept=True and you want to commit.
Requires telemetry consent.
Parameters:
uri: Browser item URI (or stable preset/sample id)
kept: Whether this candidate was kept
search_query: Optional search text that led here (e.g. "analog bass")
dwell_ms: Optional time spent auditioning
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: uri (required), kept, dwell_ms, user_prompt, +1 more. Returns: result
reject_last_actionA
Mark the last action as rejected (exploration / preference boundary).
Use when the human undoes or discards an agent edit. Requires telemetry consent.
Parameters:
reason: Optional why it was rejected
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: reason, user_prompt. Returns: result
set_arrangement_automationA
Automate a parameter across the Arrangement timeline (filter sweeps, builds, fades).
points: [{"time": beats, "value": v, "step": false}, ...] with times in absolute Arrangement beats (0 = bar 1; bar N starts at (N-1)*4 in 4/4). Between points the value ramps linearly; "step": true makes a jump.
Writes real track automation. Live's API can't create envelopes in Arrangement clips, so every MIDI clip on the track overlapping the span from the first to the last point is rebuilt through an empty Session slot (same notes, name, color, plus the curve) and duplicated back onto itself; Live turns the envelope into track automation over that clip's span. Inside a rebuilt clip the curve holds its end values outside the span; the lane outside rebuilt clips is left untouched, so cover every clip where the value should differ from the parameter's current one.
Limits: the track needs one empty Session slot and MIDI clips covering the span. Audio clips, and clips looped or trimmed inside the Arrangement, are skipped and listed under "skipped". Group tracks and audio tracks monitoring an input can't be automated through the API.
Parameters:
track_index: Track to automate
points: The curve (see above)
resolution: Step width for ramps in beats (default 0.125)
clear_existing: Kept for compatibility; the lane is always replaced over each rebuilt clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Target (what to automate):
target_type: "device" (a device parameter) or "mixer" (track mixer)
device_index, parameter_index: for "device"; discover them with get_device_parameters
mixer_name: for "mixer": "volume", "panning" or "send"
send_index: for mixer_name "send" Values are in the parameter's own units (the same min..max that get_device_parameters reports), and are clamped to that range.
Inputs: points (required), track_index (required), mixer_name, resolution, +6 more. Returns: result
set_arrangement_clip_nameA
Set the name of a clip placed in the Arrangement timeline.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip within track.arrangement_clips, in the same order returned by get_arrangement_clips (i.e. ordered by start_time)
name: The new name for the clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: name (required), clip_index (required), track_index (required), user_prompt. Returns: result
set_arrangement_timeA
Move the arrangement playhead to a specific position.
Parameters:
time: Position in beats from the start of the arrangement (e.g. 8.0 = bar 3 in 4/4)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: time (required), user_prompt. Returns: result
set_clip_automationA
Write an automation curve into one clip's envelope.
points: [{"time": beats, "value": v, "step": false}, ...] with times in clip-local
beats (0 = clip start, same timeline as note start_time). Between points the value
ramps linearly; "step": true holds the point's value until the next point (a jump).
Before the first / after the last point the end values are held, so one point
writes a flat line. Ramps are written as steps resolution beats wide.
Parameters:
track_index, clip_index, clip_view: which clip (see get_clip_automation)
points: The curve (see above)
resolution: Step width for ramps in beats (default 1/32 note = 0.125)
clear_existing: Replace the parameter's existing envelope in this clip (default True)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Target (what to automate):
target_type: "device" (a device parameter) or "mixer" (track mixer)
device_index, parameter_index: for "device"; discover them with get_device_parameters
mixer_name: for "mixer": "volume", "panning" or "send"
send_index: for mixer_name "send" Values are in the parameter's own units (the same min..max that get_device_parameters reports), and are clamped to that range.
Inputs: points (required), clip_index (required), track_index (required), clip_view, +8 more. Returns: result
set_clip_nameC
Set the name of a clip.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot containing the clip
name: The new name for the clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: name (required), clip_index (required), track_index (required), user_prompt. Returns: result
set_dataset_consentA
Record the user's answer to the dataset consent question.
Call this ONLY after the user has answered in their own words. Never infer the answer, never call it on their behalf, and never call it because contributing seems helpful — consent the user did not give is not consent. If they have not been asked yet, ask first and wait for their reply.
Parameters:
consent: True if the user agreed to contribute, False if they declined
user_said: The user's reply, quoted as closely as possible
Inputs: consent (required), user_said. Returns: result
set_device_parameterA
Set a device parameter to a specific value.
Use get_device_parameters first to discover parameter indices and ranges.
Parameters:
track_index: Track that owns the device (-1 = master track)
device_index: Index into the track's device chain
parameter_index: Index into device.parameters
value: New parameter value (Live parameter units)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: value (required), track_index (required), device_index (required), parameter_index (required), +1 more. Returns: result
set_tempoB
Set the tempo of the Ableton session.
Parameters:
tempo: The new tempo in BPM
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: tempo (required), user_prompt. Returns: result
set_track_nameA
Set the name of a track.
Parameters:
track_index: The index of the track to rename
name: The new name for the track
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: name (required), track_index (required), user_prompt. Returns: result
start_playbackB
Start playing the Ableton session.
Parameters:
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt. Returns: result
stop_clipA
Stop playing a clip.
Parameters:
track_index: The index of the track containing the clip
clip_index: The index of the clip slot containing the clip
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: clip_index (required), track_index (required), user_prompt. Returns: result
stop_playbackB
Stop playing the Ableton session.
Parameters:
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt. Returns: result
submit_intentA
Record the human's creative intent for subsequent actions in this session.
Call this before a sequence of edits so trajectory steps are conditioned on intent. Levels: 1=atomic, 2=musical op, 3=section, 4=song, 5=creative goal.
Requires telemetry consent. Data is stored in Supabase (same project as telemetry).
Parameters:
text: Natural-language intent (e.g. "make the chorus feel bigger")
level: Hierarchical intent level 1–5 (default 5)
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: text (required), level, user_prompt. Returns: result
switch_to_arrangement_viewC
Switch Ableton's main window to the Arrangement view.
Parameters:
user_prompt: The original user prompt that led to this tool call (for telemetry)
Inputs: user_prompt. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 43 tools
Most tools target a clearly distinct resource+action (clip notes, device params, transport, arrangement automation), and the session/arrangement automation trio is well delineated by the clip_view/scope parameters. The fuzzy spots are device loading (insert_device vs load_instrument_or_effect vs load_drum_kit), snapshot vs session/track info, and the preference-logging cluster (rate_last_action vs reject_last_action vs prefer_candidate) which agents could easily confuse.
Nearly everything is consistent snake_case verb-first (get_*, set_*, create_*, clear_*, delete_*, load_*), with arrangement variants named predictably against session variants. Minor deviations are duplicate_to_arrangement (object trails awkwardly) and mixed-style oddities like prefer_candidate and get_remote_script_info, but nothing breaks the pattern.
43 tools is well past the heavy threshold, and a meaningful chunk is not DAW control at all: five+ telemetry/preference instruments (submit_intent, rate_last_action, prefer_candidate, reject_last_action, record_audition, set_dataset_consent), a handshake tool, and a pure UI tool (switch_to_arrangement_view). The musical surface alone would be reasonable, but the research-instrumentation layer inflates the set.
Core workflows (tracks, clips, MIDI notes, devices, browser, automation, locators) are covered end-to-end with read/modify/write loops supported via clear_notes_from_clip. However there are notable gaps: no delete_track or track volume/pan/send setters outside automation, no scene/fire-scene management, no device removal, no clip loop/color/warp controls, and no undo — real dead ends for common mixing and arrangement tasks.
Maintenance
Related MCP Connectors
Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.
Create, co-edit, analyze, publish, and export collaborative step-sequencer sessions through MCP.
Read and edit DAW projects as an agent, save native Logic projects, convert projects between DAWs
Compose, mix, master and export in Logic Pro, REAPER or Ableton Live by talking to an AI engineer.
Related MCP Servers
- AlicenseCqualityDmaintenanceConnects Claude AI to Ableton Live through the Model Context Protocol, enabling prompt-assisted music production with track creation, instrument loading, clip editing, and session control. Allows users to create complete musical arrangements by describing what they want in natural language.373MIT
- FlicenseNot gradedqualityCmaintenanceEnables natural language control of Ableton Live through Claude, including session management, track and clip creation, device parameter adjustment, and browser browsing.1-
- AlicenseBqualityDmaintenanceConnects Ableton Live to Claude AI via the Model Context Protocol, enabling prompt-assisted music production, track creation, and Live session manipulation.16MIT
- FlicenseBqualityDmaintenanceControl Ableton Live from Claude Code via the Model Context Protocol (MCP). Create/edit tracks, control plugins, fire clips, edit MIDI notes, capture audio — all through natural language.100-