MaxMSP-MCP-Server

MaxMSP-MCP-Serverは、Model Context Protocol(MCP)を利用して、LLMがMaxパッチを直接理解し生成できるようにするプロジェクトです。LLMは、オブジェクトの公式ドキュメントや現在のパッチ内のオブジェクトにアクセスでき、デバッグやアクションの検証を行います。これにより、音楽制作や音響デザインのプロセスが効率化されます。

GitHubスター

54

ユーザー評価

未評価

フォーク

3

イシュー

2

閲覧数

0

お気に入り

0

README
MaxMSP-MCP Server

This project uses the Model Context Protocol (MCP) to let LLMs directly understand and generate Max patches.

Understand: LLM Explaining a Max Patch

img Video link. Acknowledgement: the patch being explained is downloaded from here. Text comments in the original file are deleted.

Generate: LLM Making an FM Synth

img Check out the full video where you can listen to the synthesised sounds.

The LLM agent has access to the official documentation of each object, as well as objects in the current patch and subpatch windows, which helps in retrieving and explaining objects, debugging, and verifying their own actions.

Installation
Prerequisites
  • Python 3.8 or newer
  • uv package manager
  • Max 9 or newer (because some of the scripts require the Javascript V8 engine), we have not tested it on Max 8 or earlier versions of Max yet.
Installing the MCP server
  1. Install uv:
# On macOS and Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
# On Windows:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
  1. Clone this repository and open its directory:
git clone https://github.com/tiianhk/MaxMSP-MCP-Server.git
cd MaxMSP-MCP-Server
  1. Start a new environment and install python dependencies:
uv venv
uv pip install -r requirements.txt
  1. Connect the MCP server to a MCP client (which hosts LLMs):
# Claude:
python install.py --client claude
# or Cursor:
python install.py --client cursor

To use other clients (check the list), you need to download, mannually add the configuration file path to here, and connect by running python install.py --client {your_client_name}.

Installing to a Max patch

Use or copy from MaxMSP_Agent/demo.maxpat. In the first tab, click the script npm version message to verify that npm is installed. Then click script npm install to install the required dependencies. Switch to the second tab to access the agent. Click script start to initiate communication with Python. Once connected, you can interact with the LLM interface to have it explain, modify, or create Max objects within the patch.

Disclaimer

This is a third party implementation and not made by Cycling '74.

作者情報
Haokun Tian

AI & Music PhD student @ Center for Digital Music (c4dm) @ Queen Mary University of London

London

16

フォロワー

17

リポジトリ

0

Gist

37

貢献数

トップ貢献者

スレッド