ableton-live-mcp-server

ableton-live-mcp-server

Enables LLMs to control Ableton Live via OSC and the Model Context Protocol, supporting commands like setting up tracks and routing.

Category
访问服务器

README

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.

ontrol 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.

✨ 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

Option 1: Install with UV (Recommended)

  1. Install UV if you don't have it already:

    pip install uv
    
  2. Install directly from PyPI:

    uv install ableton-live-mcp-server
    
  3. Or install from GitHub:

    uv install git+https://github.com/yourusername/ableton-live-mcp-server.git
    

Option 2: Manual Installation

  1. Install uv
    pip install uv
    
  2. Clone the repository:
    git clone https://github.com/your-username/mcp_ableton_server.git
    cd mcp_ableton_server
    
  3. Install dependencies:
    uv install python-osc fastmcp
    
  4. Install the MCP Server This assumes that you're using Claude Desktop
    mcp install mcp_ableton_server.py
    
  5. 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:

# If installed via UV:
ableton-osc-daemon

# Or if running from source:
python 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.

Running the MCP Server

Start the MCP server to enable LLMs to control Ableton:

# If installed via UV:
ableton-mcp-server

# Or if running from source:
python mcp_ableton_server.py

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 or use command-line parameters:

ableton-osc-daemon --socket-port 65432 --ableton-port 11000 --receive-port 11001

Claude Desktop Configurations

  • macOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"Ableton Live Controller": {
      "command": "uv",
      "args": [
        "run",
        "ableton-mcp-server"
      ]
    }
  }

Contributing

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

Publishing Updates

To publish new versions using UV:

  1. Update the version in pyproject.toml
  2. Build the package:
    uv build
    
  3. Publish to PyPI:
    uv publish
    

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.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选