Blender add-on and MCP server that let AI assistants like Claude build, modify and inspect 3D scenes in Blender through prompts.
ahujasid/ableton-mcp
An MCP server and Ableton Live Remote Script that let LLM clients like Claude create tracks, load instruments, and compose clips in Ableton Live.
- Stars
- 3,211
- Forks
- 465
- Open issues
- 48
- Last commit
- 28 days ago
What is it?
Ableton MCP connects Ableton Live to large language model clients such as Claude Desktop and Cursor using the Model Context Protocol. It has two parts: a Python MCP server that exposes tools to the model, and an Ableton Remote Script that runs a socket server inside Live and executes the commands it receives.
Once connected, a user can ask the model to inspect the current session, create MIDI or audio tracks, load instruments and effects from Ableton's browser, add notes to MIDI clips, change tempo, and start or stop playback. The project also supports building full song structures such as intro, buildup, drop, breakdown and outro in Arrangement View.
Installation uses uv, with a bundled installer that copies the Remote Script into Ableton's User Library. The project is a third-party integration and is not made by Ableton. Anonymous usage telemetry is on by default and can be disabled; dataset recording of prompts and MIDI content is opt-in.
Key features
- 01Creates and modifies MIDI and audio tracks in Ableton Live.
- 02Loads instruments and effects from Ableton's browser.
- 03Adds and edits notes in MIDI clips.
- 04Builds full song arrangements in Arrangement View.
- 05Controls playback, clip triggering and tempo.
Use cases
- Prototyping a beat or track by describing it to an LLM.
- Automating repetitive session setup such as loading drum racks and adding effects.
- Experimenting with AI-assisted arrangement and melody generation inside Live.
Quick start
- 1
Install uv (macOS via Homebrew)
brew install uv - 2
Add the MCP server to your client config (e.g. Claude Desktop)
- 3
Install the Ableton Remote Script
uvx --from ableton-mcp ableton-mcp-install-script - 4
In Ableton Live, select AbletonMCP as the Control Surface and set Input and Output to None
Things to know
- Requires Ableton Live 10 or newer and Python 3.8 or newer.
- Works best with Ableton's default devices and browser items.
- Complex arrangements may need to be broken into smaller steps.
- Anonymous telemetry is on by default and can be disabled with an environment variable.
Topics
FAQ
- What is ableton-mcp?
- An MCP server and Ableton Live Remote Script that let LLM clients like Claude create tracks, load instruments, and compose clips in Ableton Live. Ableton MCP connects Ableton Live to large language model clients such as Claude Desktop and Cursor using the Model Context Protocol. It has two parts: a Python MCP server that exposes tools to the model, and an Ableton Remote Script that runs a socket server inside Live and executes the commands it receives.
- Is ableton-mcp free to use? What license does it have?
- ableton-mcp is open source under the MIT license. Check the license terms before using it in commercial products.
- Is ableton-mcp still maintained?
- Actively maintained. The last commit to ableton-mcp was on Sep 22, 2026.
- What can I use ableton-mcp for?
- Prototyping a beat or track by describing it to an LLM. Automating repetitive session setup such as loading drum racks and adding effects. Experimenting with AI-assisted arrangement and melody generation inside Live.
- How do I install ableton-mcp?
- Install uv (macOS via Homebrew): brew install uv Add the MCP server to your client config (e.g. Claude Desktop) Install the Ableton Remote Script: uvx --from ableton-mcp ableton-mcp-install-script In Ableton Live, select AbletonMCP as the Control Surface and set Input and Output to None
- Where can I get ableton-mcp?
- The source code and installation instructions are on GitHub: https://github.com/ahujasid/ableton-mcp
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Python SDK for building agents on Claude Code, with query(), an interactive client, in-process custom tools and hooks.
On-screen AI assistant for desktop that reads the current app's context and uses multiple LLMs and MCP tools to help you act across apps.
A CLI that scans your codebase and generates compact AI context files (CLAUDE.md, .cursorrules, AGENTS.md) so coding assistants spend fewer tokens exploring the project.
An MCP server that lets AI assistants like Claude and Cursor run web searches through a SearXNG instance you operate or trust.
Agent-native memory infrastructure that turns LLM agent conversations and execution into persistent, structured memory for Python and TypeScript apps.