home / mcp / ableton mcp extended mcp server
Provides programmatic control of Ableton Live via MCP, translating natural language commands into live session actions.
Configuration
View docs{
"mcpServers": {
"uisato-ableton-mcp-extended": {
"command": "python",
"args": [
"C:/path/to/ableton-mcp-extended/MCP_Server/server.py"
]
}
}
}Ableton MCP Extended lets you control Ableton Live with natural language through AI assistants. It translates your spoken or typed commands into precise actions inside your Live session, enabling faster workflow, experimentation with generative ideas, and custom integrations.
You connect an AI assistant to an MCP server that speaks Ableton Live in its native language. Start by installing the MCP server locally, then point your assistant to the running server. Use plain English prompts like “Create a new MIDI track named Bass,” “Add a drum loop,” or “Load a piano instrument on Track 1.” The MCP server converts your request into a structured command that the Ableton Remote Script executes inside Live. Real-time feedback appears in your session as new tracks, clips, devices, or automation points are created or updated.
Practical usage patterns you can follow: - Create and name tracks or clips. - Load instruments and effects from Ableton’s browser by URI or path. - Adjust track volume, panning, mute, solo, and arm. - Fire scenes and manage the session tempo and time signature. - Generate voice or narration using integrated text-to-speech and import it directly into the session. - Build custom tools and interfaces atop the MCP framework for ultra-low latency control.
Prerequisites: Ableton Live 11+, Python 3.10 or higher, and an AI assistant that can connect to MCP (such as Claude Desktop or Cursor IDE).
# 1) Get the code
git clone https://github.com/uisato/ableton-mcp-extended.git
cd ableton-mcp-extended
pip install -e .
# 2) Install Ableton Script (exact paths will vary by system)
# Windows example
# Create folder: C:\Users\[You]\Documents\Ableton\User Library\Remote Scripts\
# Copy AbletonMCP_Remote_Script/__init__.py into this folder
# Mac example
# Folder: ~/Library/Preferences/Ableton/Live [Version]/User Remote Scripts/
# 3) Configure Ableton
# In Ableton Live, set Preferences > Link, Tempo & MIDI
# Set Control Surface to "AbletonMCP" and set Input/Output to "None"
# 4) Connect AI Assistant
# For Claude Desktop
{
"mcpServers": {
"AbletonMCP": {
"command": "python",
"args": ["C:/path/to/ableton-mcp-extended/MCP_Server/server.py"]
}
}
}
# For Cursor, add the MCP server in Settings → MCP with the same path
# 5) Start creating
# In your assistant, try prompts like:
# - "Create a new MIDI track with a piano"
# - "Add a simple drum beat"
# - "What tracks do I currently have?"If you plan to use ElevenLabs voice integration or other extended tools, you can extend the MCP configuration to include those servers. The Ableton MCP Extended framework supports loading instruments and effects, generating spoken audio, and importing generated content directly into your Live session.
Start and stop playback, query transport state, and control scene firing to move your session forward or pause the performance.
Create, rename, and get details for MIDI and audio tracks; adjust volume, pan, mute, solo, and arm; manage track groups and folding.
Create MIDI clips, name them, specify lengths, and add, delete, transpose, and quantize notes; perform batch edits across multiple notes.
Load instruments and effects by URI, get device parameter lists, and set parameters with normalized values.
Add and clear automation points within a clip and inspect existing clip envelopes.
Navigate Ableton’s browser, load instruments/effects from paths or URIs, and import audio into tracks or clips.
Text-to-speech integration to generate narration or spoken audio, with direct import into the session.
Provide a framework to build custom MCP tools and controllers, enabling ultra-low-latency control via UDP or TCP.
Example showing how to create a custom Ableton controller for precise parameter interaction.