Ableton for AI

[!IMPORTANT] For AI Agents: Please read AGENTS.md for detailed technical context and protocol specifications before working on this project.

Ableton for AI is the bridge between your DAW and AI models. It makes Ableton projects hearable and visible to AI models by implementing the Model Context Protocol (MCP) and exporting detailed project data.

What can it do?

Connect Ableton Live directly to MCP-capable AI clients (like Claude Desktop, Cursor, or Cline). The AI can inspect, analyze, and even modify your project in real-time.

Included Tools:

• get_overview: SESSION DISCOVERY. Provides tempo, locators, and a list of all tracks with their current mixer state (volume, panning, etc.).
• get_track: TRACK INSPECTION. Comprehensive data for a single track: metadata, complete device chain, and all device parameters (with UI-readable strings).
• get_tracks: BULK TRACK INSPECTION. Query full data for a range of tracks in a single parallelized call.
• analyze_stems: DEEP AUDIO ANALYSIS. Triggers generation of audio summaries (.summary.json) and spectrograms (.spectrogram.webp) for all tracks.
• set_track_volume / set_track_panning: MIXER CONTROL. Remotely adjust track faders and panning.
• set_device_parameter: REMOTE CONTROL. Precisely adjust any parameter of any device in the project.

Included Resources:

• ableton://stems/{track_name}/summary: AUDIO SUMMARY. Compact analysis (JSON) containing LUFS, Peak, RMS, 10ms-frames, detected transients, and a legend field.
• ableton://stems/{track_name}/spectrogram: VISUAL ANALYSIS. Log-frequency spectrogram image (WebP) for visual frequency inspection.
• ableton://stems/available/summaries: Discovery resource for all tracks with available audio summaries.
• ableton://stems/available/spectrograms: Discovery resource for all tracks with available spectrograms.

How do I get started?

1. Prepare your environment

Install AbletonOSC

This project relies on AbletonOSC to communicate with Ableton Live.

• Download and install AbletonOSC.
• Follow the instructions there to add it as a Control Surface in Ableton Live's Link/Tempo/MIDI settings.

Install ableton-for-ai

Option A: uv (Recommended)

uv lets you run the server directly without installing anything globally:

brew install uv          # macOS (Homebrew)
# or: curl -LsSf https://astral.sh/uv/install.sh | sh   (macOS/Linux)
# or: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"  (Windows)

Option B: pip

Requires Python 3.11+ (python.org or brew install python):

pip install ableton-for-ai

2. Connect to your Chatbot (MCP Client)

Add the server to your MCP client configuration (e.g. Claude Desktop, Cursor, or Cline).

Via uvx (if you installed uv)

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

Via pip (if you installed with pip)

{
  "mcpServers": {
    "ableton-for-ai": {
      "command": "ableton-for-ai",
      "env": {
        "STEMS_SOURCE_DIR": "/path/to/your/exported/stems"
      }
    }
  }
}

[!NOTE] STEMS_SOURCE_DIR must point to the folder where your exported audio stems are located. You need to export stems manually from Ableton Live (e.g. via "Export Audio/Video" with individual tracks selected), as there is currently no OSC API for triggering exports. The audio analysis tools (analyze_stems) will look for files in this directory.

Where to put this config

• Claude Desktop (macOS): `~/Library/Application Support/Claude/claude

... View full README on GitHub