ahujasid/ableton-mcp

Control Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP

What it solves

It enables AI assistants like Claude to directly control Ableton Live, allowing users to produce music, create tracks, and manipulate session arrangements through natural language prompts rather than manual clicking and dragging.

How it works

The project uses a two-part system: a Python-based MCP (Model Context Protocol) server that interfaces with an AI client (like Claude Desktop or Cursor) and a custom MIDI Remote Script installed directly into Ableton Live. These two components communicate via a JSON-based protocol over TCP sockets, allowing the AI to send commands that the Remote Script executes within the DAW.

Who it’s for

Music producers and composers who want to use AI to accelerate their workflow, automate repetitive arrangement tasks, or experiment with prompt-driven music creation.

Highlights

  • End-to-end track creation: Build full songs in Arrangement View, including sections like intros, drops, and outros.
  • DAW manipulation: Create and modify MIDI/audio tracks, load instruments and effects from the Ableton library, and change tempo.
  • Clip management: Create, edit, and trigger MIDI clips and add specific notes to them.
  • Session control: Start and stop playback and fire clips across both Session and Arrangement views.

Related

  • Project
    marcelmarais/spotify-mcp-server

    Spotify MCP Server is a Node.js service that implements the Model Context Protocol for Spotify, exposing a rich set of read, playback, album, playlist, and user‑library operations. It lets AI assistants like Claude or Cursor control Spotify (search, play, create playlists, adjust volume, etc.) via MCP over stdio or HTTP, with OAuth handling and Docker support.

  • Project
    adamjmurray/producer-pal

    An Ableton MCP server and REST API that allows users to control Ableton Live using natural language via AI assistants or custom scripts.

  • Project
    domdomegg/computer-use-mcp

    An MCP server that allows Claude and other AI models to control a local computer via keyboard and mouse automation.

  • Project
    tomyud1/godot-mcp

    A Model Context Protocol (MCP) server that gives AI assistants direct access to the Godot editor to read, write, and manipulate scenes, scripts, and project settings.

  • Project
    pipeboard-co/meta-ads-mcp

    An MCP server that enables AI assistants to launch, manage, and analyze Meta Ads campaigns across Facebook and Instagram through natural conversation.