Ableton for AI MCP Server

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        return os.path.join(self.BASE_OUT_DIR, self.PROJECT_DIR, self.PROJECT_JSON_FILENAME)

        out = subprocess.check_output(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add ableton-for-ai -- uvx ableton-for-ai

{
  "mcpServers": {
    "ableton-for-ai": {
      "args": [
        "ableton-for-ai"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.ableton-for-ai]
command = "uvx"
args = ["ableton-for-ai"]

{
  "mcpServers": {
    "ableton-for-ai": {
      "args": [
        "ableton-for-ai"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "ableton-for-ai": {
      "args": [
        "ableton-for-ai"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: STEMS_SOURCE_DIR (Path to the folder containing exported audio stems), PREFERRED_AUDIO_FORMAT (Audio format of your stems (wav or mp3)). The author declared them in the registry entry; get the values from the project itself.