A coding agent for Max (Max/MSP/Jitter), which is a visual programming language for music and multimedia.
Add to Claude Desktop config.json
{
"mcpServers": {
"tiianhk-maxmsp-mcp-server": {
"command": "node",
"args": [
"~/.mcp/MaxMSP-MCP-Server/index.js"
]
}
}
} Get the source and run locally
git clone https://github.com/tiianhk/MaxMSP-MCP-Server.git ~/.mcp/MaxMSP-MCP-Server
cd ~/.mcp/MaxMSP-MCP-Server Note: An extended version by ersatzben and BenCello can be found at: https://github.com/ersatzben/maxmsp-mcp
This project uses the Model Context Protocol (MCP) to let LLMs directly understand and generate Max patches.
Video link. Acknowledgement: the patch being explained is downloaded from here. Text comments in the original file are deleted.
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.
# 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"
git clone https://github.com/tiianhk/MaxMSP-MCP-Server.git
cd MaxMSP-MCP-Server
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt
# 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}.
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.
This is a third party implementation and not made by Cycling ‘74.
A fully-featured coding agent that relies on symbolic code operations by using language servers.
An MCP server that indexes local code into a graph database to provide context to AI assistants with a graphical code visualizations for humans.
Coding agent with basic read, write and command line tools.
Desktop GUI automation using accessibility APIs. Control Windows, macOS, and Linux applications without vision models or screenshots. Supports workflow recording, structured data extraction, and browser DOM inspection.
A framework for creating multi-agent systems using MCP for coordinated AI collaboration, featuring task management, shared context, and RAG capabilities.
A MCP Server that allows AI such as Claude to read from the directory structure in a VS Code workspace, see problems picked up by linter(s) and the language server, read code files, and make edits.