Ableton For Ai

Please install the `ableton-for-ai` MCP server into my current AI client (that's you).

Optional prerequisites:
- Install AbletonOSC — Install AbletonOSC and add it as a Control Surface in Ableton Live's Link/Tempo/MIDI settings so the MCP server can communicate with Ableton Live. (https://github.com/ideoforms/AbletonOSC},{)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["ableton-for-ai"]
- required environment variables:
  - `STEMS_SOURCE_DIR`: Path to the folder containing manually exported Ableton audio stems. Required in practice for the default workflow and audio analysis features. (example: `<path-to-your-exported-stems>`)
- optional environment variables:
  - `LOG_LEVEL`: Logging verbosity. (example: `<INFO-or-DEBUG>`)
  - `BASE_OUT_DIR`: Directory for project data and analysis results. (example: `<path-to-output-directory>`)
  - `PREFERRED_AUDIO_FORMAT`: Audio format to analyze. (example: `<mp3-or-wav>`)
  - `SPECTROGRAM_QUALITY`: Quality of WebP spectrograms from 1 to 100. (example: `<1-100>`)

Note: Preferred portable install path is via uv/uvx. Alternative pip install exists, which would use command `ableton-for-ai` with no args. Additional configuration values `RELEVANT_DEVICE_CLASSES` and `RELEVANT_DEVICE_NAMES` are documented in config.py-oriented settings, but the README does not provide a clear portable MCP env encoding for those collection values. For custom VST exposure, Ableton may require adding `-_PluginAutoPopulateThreshold=128` to Ableton's Options.txt. Stems must be exported manually from Ableton Live into `STEMS_SOURCE_DIR`.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.