Ableton For Ai

Name: Ableton For Ai
Author: peterkolbe

@peterkolbe

About Ableton For Ai

Bridge between Ableton Live and AI models. Inspect tracks, analyze audio (LUFS, spectrograms), and control mixing parameters in real-time via MCP.

#mcp #ableton #ableton-live #music-production #audio-analysis #daw #mixing #osc #ai #spectrograms #stems #music

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ableton-for-ai": {
      "command": "uvx",
      "args": [
        "ableton-for-ai"
      ],
      "env": {
        "STEMS_SOURCE_DIR": "/path/to/your/stems"
      }
    }
  }
}

Tools

List resources available on the server.

Read a resource available on the server.

DEEP AUDIO ANALYSIS: Triggers the generation of summaries and spectrograms for all tracks. This is a heavy operation that: 1. Generates '.summary.json' (Frames, Transients, LUFS) for AI consumption. 2. Generates '.spectrogram.webp' (Log-frequency visualizations). 3. Generates '.analysis.json' (Full resolution data for internal use). ACTION: Use this when you need fresh audio data (e.g., after the user recorded new parts or changed audio effects that significantly alter the sound).

SESSION DISCOVERY: Returns a high-level overview of the current Live set. Includes: - Tempo and Locators (Song structure). - Simplified Track list with mixer states (Index, Name, Volume, Panning, Mute, Solo). Use this for initial navigation and to identify track indices for further 'get_track' calls.

TRACK INSPECTION: Returns comprehensive data for a single track. Includes: - Mixer state (Volume, Panning, etc.). - Complete Device Chain. - All Device Parameters (including UI-readable strings like "-12.0 dB" or "1500 Hz"). Use this when you need to understand exactly how a specific track is processed or which parameters are available for manipulation.

BULK TRACK INSPECTION: Query full data for multiple tracks in a single call. Parameters: - index_min: Starting track index. - index_max: Ending track index. Returns an array of track objects, identical in structure to 'get_track'. Highly efficient for analyzing groups of tracks (e.g., all drum tracks).

REMOTE CONTROL: Sets a specific device parameter. Parameters: - track_index: The index of the track. - device_index: The index of the device in the chain. - parameter_index: The index of the parameter to change. - value: The new normalized value (0.0 to 1.0). Note: For UI-readable values (like dB or Hz), check 'get_track' output first, but always send the normalized 0.0-1.0 value for the actual change.

BULK REMOTE CONTROL: Sets multiple parameters for a device at once. Parameters: - values: A list of floats representing the new values for ALL parameters of the device. Recommended for loading 'presets' or making simultaneous multi-parameter adjustments.

MIXER CONTROL: Sets the volume of a track. - value: 0.0 to 1.0 (corresponds to Ableton's internal fader scaling).

MIXER CONTROL: Sets the panning of a track. - value: -1.0 (Left) to 1.0 (Right), 0.0 is Center.

Toggles the mute status of a track (True=Muted, False=Active).

Toggles the solo status of a track (True=Solo, False=Normal).

Overview

What is Ableton For Ai?

Ableton For Ai is an MCP server that bridges Ableton Live and AI models, enabling real-time inspection, analysis, and modification of music projects. It makes a running Ableton session hearable and visible to AI via OSC.

How to use Ableton For Ai?

Install the server with Python 3.11+ and AbletonOSC as a Control Surface in Ableton Live 11 or 12. Invoke MCP tools such as get_overview, analyze_stems, set_track_volume, and set_device_parameter to interact with the session.