ableton-proj

This MCP server parses Ableton Live .als project files and exposes structured metadata about BPM, track structure, device inventory (stock Ableton devices and third-party plugins), and references to samples for easier batch relinking and project analysis. It includes core tools to scan directories for Ableton projects, analyze individual projects deeply, and perform enhanced analyses like duplicate detection and missing plugins or samples across a collection of projects. The server is designed to run locally and to surface rich JSON outputs that can be consumed by scripting, tooling, or automation workflows.

Prerequisites:

• Python 3.10 or newer
• uv (the MCP runtime tool) installed on your system

1. Install uv per the project instructions:

   curl -LsSf https://astral.sh/uv/install.sh | sh

2. Clone or download the Ableton Project MCP Server repository and open a terminal in the project root.

3. Ensure you have a working path to your MCP server so you can reference it from uv commands if needed. The server is designed to be run locally and expects access to your Ableton .als files.

4. (Optional) If you use Claude Desktop or similar tooling, configure it to point at your local MCP server as shown in the README example, replacing paths with your actual server location.

5. Start using the MCP server via uv (as described in the mcp_config example).

Notes and tips:

• The server processes gzip-compressed Ableton .als files and exposes JSON metadata. Deep analysis may be slower; batch sizes should be tuned using environment/configuration values if available.
• If you encounter missing plugin names or device detection issues, ensure the .als files originate from Ableton Live 11+ and that plugin metadata is accessible in the environment where the analysis runs.
• You can adjust safety and performance parameters (e.g., maximum files to scan, file size limits, scan depth) in the source constants (as described in the README) to suit larger collections or constrained environments.
• The server supports enhanced analysis like duplicate detection and master chain comparisons across projects, which can help with migrations, archiving, and quality control.
• Since the MCP outputs are JSON, you can pipe results into scripts, dashboards, or data stores for automation.
• If you see timeouts or long processing times, try reducing the batch size or performing scans on smaller directories first.