Skip to main content
Glama

Ableton Live MCP Server

📌 Overview

The Ableton Live MCP Server is a server implementing the Model Context Protocol (MCP) to facilitate communication between LLMs and Ableton Live. It uses OSC (Open Sound Control) to send and receive messages to/from Ableton Live. It is based on AbletonOSC implementation and exhaustively maps available OSC adresses to tools accessible to MCP clients.

Control Ableton Live with LLMs

This project consists of two main components:

  • mcp_ableton_server.py: The MCP server handling the communication between clients and the OSC daemon.

  • osc_daemon.py: The OSC daemon responsible for relaying commands to Ableton Live and processing responses.

Related MCP server: Ableton MCP Extended

✨ Features

  • Provides an MCP-compatible API for controlling Ableton Live from MCP clients.

  • Uses python-osc for sending and receiving OSC messages.

  • Based on the OSC implementation from AbletonOSC.

  • Implements request-response handling for Ableton Live commands.

⚡ Installation

Requirements

  • Python 3.8+

  • python-osc (for OSC communication)

  • fastmcp (for MCP support)

  • uv (recommended Python package installer)

  • AbletonOSC as a control surface

Installation Steps

  1. Install uv (https://docs.astral.sh/uv/getting-started/installation):

    curl -LsSf https://astral.sh/uv/install.sh | sh
  2. Clone the repository:

    git clone https://github.com/your-username/mcp_ableton_server.git
    cd mcp_ableton_server
  3. Install the project and its dependencies:

    uv sync
  4. Install AbletonOSC Follow the instructions at AbletonOSC

🚀 Usage

Running the OSC Daemon

The OSC daemon will handle OSC communication between the MCP server and Ableton Live:

uv run osc_daemon.py

This will:

  • Listen for MCP client connections on port 65432.

  • Forward messages to Ableton Live via OSC on port 11000.

  • Receive OSC responses from Ableton on port 11001.

Example Usage

In Claude desktop, ask Claude:

  • Prepare a set to record a rock band

  • Set the input routing channel of all tracks that have "voice" in their name to Ext. In 2

⚙️ Configuration

By default, the server and daemon run on localhost (127.0.0.1) with the following ports:

  • MCP Server Socket: 65432

  • Ableton Live OSC Port (Send): 11000

  • Ableton Live OSC Port (Receive): 11001

To modify these, edit the AbletonOSCDaemon class in osc_daemon.py:

self.socket_host = '127.0.0.1'
self.socket_port = 65432
self.ableton_host = '127.0.0.1'
self.ableton_port = 11000
self.receive_port = 11001

Claude Desktop Configuration

To use this server with Claude Desktop, you need to configure it in your Claude Desktop settings. The configuration file location varies by operating system:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration to your mcpServers section:

{
  "mcpServers": {
    "Ableton Live Controller": {
      "command": "/path/to/your/project/.venv/bin/python",
      "args": ["/path/to/your/project/mcp_ableton_server.py"]
    }
  }

This configuration ensures that:

  • The server runs with all dependencies properly managed

  • The project remains portable and reproducible

Contributing

Feel free to submit issues, feature requests, or pull requests to improve this project.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgments

TODO

  • Explore resources and prompts primitives opportunities.

  • Build a standalone Ableton Live MCP client.


Available Tools

1 tool
get_track_namesB
Get the names of tracks in Ableton Live.

Args:
    index_min: Optional minimum track index
    index_max: Optional maximum track index

Returns:
    A formatted string containing track names
ParametersJSON Schema
NameRequiredDescriptionDefault
index_minNo
index_maxNo

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the return format ('formatted string') but lacks critical details like whether this is a read-only operation, potential errors, performance characteristics, or how it interacts with Ableton Live's state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficiently structured with clear sections (Args, Returns) and uses minimal, purposeful sentences. Every element serves a clear function without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read operation with 2 parameters and no output schema, the description covers the basic purpose and parameters adequately. However, it lacks important context about the return format details, error conditions, and behavioral characteristics that would help an agent use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description explicitly documents both parameters (index_min, index_max) with their optional nature and purpose, adding significant value beyond the schema which has 0% description coverage. This compensates well for the schema's lack of parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and resource 'names of tracks in Ableton Live', making the purpose specific and understandable. However, without sibling tools, there's no opportunity to distinguish from alternatives, preventing a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It simply states what the tool does without context for usage decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedget_track_names

TDQS

B3.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'get_track_names' has a clearly defined and distinct purpose.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'get_track_names' follows a clear verb_noun pattern.

Tool Count2/5

A single tool for an 'Ableton Live MCP Server' feels severely underpowered and incomplete. This server appears to control a complex digital audio workstation, yet only offers track name retrieval with no ability to modify tracks, manage clips, control playback, or perform other essential DAW operations.

Completeness1/5

The tool surface is extremely incomplete for an Ableton Live integration. There are massive gaps: no track creation/deletion, no clip manipulation, no transport controls (play/stop/record), no device management, no mixer controls, and no session/scene operations. This single read-only tool provides almost no practical workflow coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers