ableton-mcp

ableton-mcp

Connects Ableton Live to Claude AI through the Model Context Protocol, enabling AI-assisted music production and Live session manipulation via over 200 tools.

Category
访问服务器

README

AbletonMCP - Ableton Live Model Context Protocol Integration

smithery badge

AbletonMCP connects Ableton Live to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Ableton Live. This integration enables AI-assisted music production, track creation, and Live session manipulation.

200+ tools for near-complete Ableton Live Object Model (LOM) coverage including AI-powered music generation.

Three Ways to Use AbletonMCP

Method Best For Requirements
MCP Server (Claude Desktop / Cursor) Claude AI integration Claude Desktop or Cursor
REST API (Ollama / OpenAI / Any LLM) Any LLM, custom apps Python, FastAPI
Max for Live Device In-Ableton AI chat Ableton Suite / M4L

Features

Transport & Session

  • Play, stop, record, overdub, capture MIDI, tap tempo, continue playing
  • Tempo, time signature, metronome, count-in, swing, groove
  • Arrangement loop, locators, jump to time, scrub

Track Control

  • Create/delete/duplicate MIDI, audio, group, and return tracks
  • Volume, pan, mute, solo, arm, color, monitoring, delay
  • Freeze/flatten, fold/unfold groups, implicit arm
  • Input/output routing, crossfade assign
  • Multi-track operations: solo exclusive, unsolo all, unmute all, unarm all

Clip Operations

  • Create/delete/duplicate/fire/stop clips
  • Loop settings, start/end markers, gain, pitch, color
  • Warp modes, warp markers, RAM mode
  • Launch modes, launch quantization, follow actions
  • Clip fades (in/out), trigger quantization
  • Playing position, velocity amount

MIDI Editing

  • Add/remove/transpose notes, get notes in range
  • Move notes (time + pitch shift), replace all notes
  • Quantize, deselect all, duplicate loop
  • Select all notes, set clip notes

Devices & Effects

  • Load instruments/effects from browser, toggle on/off, delete
  • Get/set any device parameter, device presets
  • Move devices (left/right/to position), collapse/expand
  • Rack chains, rack macros, drum rack pads (mute/solo/name)
  • Simpler/Sampler sample info and parameters

Scene Management

  • Create/delete/duplicate/fire/stop scenes, color, name

Automation

  • Clip automation envelopes (get/set/clear)
  • Session automation record, arrangement overdub
  • Re-enable automation

Browser

  • Navigate browser tree, search, load items
  • Browse by path, get children, categories

View & Selection

  • Focus view (Session/Arrangement/Detail)
  • Select track/scene/clip/device
  • Detail clip, highlighted clip slot
  • Draw mode, follow mode, grid quantization, zoom

Recording

  • Arm, record, overdub, capture MIDI
  • Session/arrangement record modes
  • MIDI recording quantization

Mixing

  • Track/master output metering (L/R)
  • Send levels, pre/post send
  • Return track volume/pan
  • Master volume/pan, cue volume
  • Crossfader position

Song Properties

  • Root note, scale, signature
  • Groove amount, exclusive arm/solo
  • Punch in/out, back to arrangement
  • Record mode, can capture MIDI

AI Music Helpers

  • Scale reference (12+ scale types)
  • Drum pattern generation (8 styles: house, techno, hip-hop, trap, dnb, jazz, funk, basic)
  • Bassline generation (6 styles: basic, walking, synth, funk, octave, arpeggiated)
  • Quantize/humanize timing and velocity

Installation

Prerequisites

Install uv:

# macOS
brew install uv

# Other platforms
# See https://docs.astral.sh/uv/getting-started/installation/

Claude Desktop Configuration

Add to your claude_desktop_config.json:

Location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
    "mcpServers": {
        "AbletonMCP": {
            "command": "uvx",
            "args": ["ableton-mcp"]
        }
    }
}

Installing via Smithery

npx -y @smithery/cli install @ahujasid/ableton-mcp --client claude

Installing the Ableton Remote Script

  1. Download AbletonMCP_Remote_Script/__init__.py from this repo

  2. Copy to Ableton's MIDI Remote Scripts directory:

    macOS:

    • Right-click Ableton Live app > Show Package Contents > Contents/App-Resources/MIDI Remote Scripts/
    • Or: /Users/[Username]/Library/Preferences/Ableton/Live XX/User Remote Scripts

    Windows:

    • C:\Users\[Username]\AppData\Roaming\Ableton\Live x.x.x\Preferences\User Remote Scripts
    • Or: C:\ProgramData\Ableton\Live XX\Resources\MIDI Remote Scripts\
  3. Create a folder called AbletonMCP in the Remote Scripts directory

  4. Paste the __init__.py file into the AbletonMCP folder

  5. Launch Ableton Live

  6. Go to Settings > Link, Tempo & MIDI

  7. In Control Surface dropdown, select "AbletonMCP"

  8. Set Input and Output to "None"

Cursor Integration

Go to Cursor Settings > MCP and add:

uvx ableton-mcp

Usage Guide

Getting Started

  1. Ensure the Ableton Remote Script is loaded (look for "AbletonMCP" in Control Surface)
  2. Configure Claude Desktop or Cursor with the MCP server
  3. Start chatting with Claude about your music production needs

Example Workflows

Create a Beat

"Create a hip-hop drum pattern at 90 BPM with a 808 kit"

Build a Full Track

"Create a raw hypnotic techno track at 135 BPM with kick, hats, clap, bass, and acid lead"

Mix and Arrange

"Add reverb to the drums, set up a sidechain send, and create intro/verse/chorus/outro scenes"

Sound Design

"Load a Simpler on track 3, show me the sample parameters, and adjust the filter"

AI Music Generation

Generate Drum Patterns

Available styles: basic, house, techno, hip_hop, trap, dnb, jazz, funk

Generate Basslines

Available styles: basic, walking, synth, funk, octave, arpeggiated

Get Scale Notes

Available scales: major, minor, dorian, phrygian, lydian, mixolydian, aeolian, locrian, harmonic_minor, melodic_minor, pentatonic_major, pentatonic_minor, blues

REST API (Ollama & Other LLMs)

AbletonMCP includes a REST API for use with any LLM provider.

Quick Start with Ollama

  1. Install Ollama: https://ollama.ai
  2. Pull a model: ollama pull llama3.2
  3. Install dependencies: pip install fastapi uvicorn pydantic
  4. Start the server: python MCP_Server/rest_api_server.py
  5. Run interactive chat: python examples/ollama_example.py

REST API Features

  • 200+ commands whitelisted and validated
  • API key authentication (optional, via REST_API_KEY env var)
  • Rate limiting (configurable per-IP)
  • CORS configured for localhost by default
  • Pagination on list endpoints (scenes, tracks, device parameters)
  • OpenAI-compatible tool definitions at /tools

Key Endpoints

Endpoint Method Description
/health GET Check Ableton connection
/tools GET Get LLM tool definitions
/api/session GET Session info
/api/tracks GET List all tracks (with pagination)
/api/scenes GET List all scenes (with pagination)
/api/command POST Execute any command
/docs GET Interactive Swagger docs

Supported LLM Providers

Provider Cost Setup
Ollama Free (local) ollama pull llama3.2
Groq Free tier API key from console.groq.com
OpenAI Paid API key from platform.openai.com
Claude API Paid API key from console.anthropic.com

Max for Live Device

For a fully integrated experience inside Ableton, use the Max for Live device.

Features

  • Multi-provider support (Ollama, OpenAI, Claude API, Groq)
  • Visual chat UI inside Ableton's device view
  • 200+ tool definitions for complete LOM control
  • No external server needed

Installation

  1. Copy AbletonMCP_M4L folder to:

    • macOS: ~/Music/Ableton/User Library/Presets/Audio Effects/Max Audio Effect/
    • Windows: Documents\Ableton\User Library\Presets\Audio Effects\Max Audio Effect\
  2. Build the .amxd binary (the repo includes a .maxpat source file):

    python3 scripts/build_amxd.py
    

    Or rename AbletonMCP.amxd.maxpat to AbletonMCP.amxd

  3. Drag onto any track in Ableton Live

  4. Select your AI provider and start chatting!

See AbletonMCP_M4L/README.md for detailed setup.

Documentation

  • MANUAL.md - Complete command reference with examples and a step-by-step techno track tutorial
  • CONFIG.md - Configuration and environment variables

Troubleshooting

Connection Issues

  • Verify AbletonMCP is selected in Ableton's Control Surface settings
  • Check that no other application is using port 9877
  • Restart both Claude and Ableton Live

Timeout Errors

  • Break complex requests into smaller steps
  • Allow time for Ableton to process commands

Script Not Loading

  • Ensure the __init__.py file is in a folder named exactly AbletonMCP
  • Check Ableton's Log.txt for errors

Commands Not Working

  • Make sure you're requesting actions on valid track/clip indices
  • Check that clips exist before trying to edit notes
  • Verify devices are loaded before adjusting parameters

Technical Details

Communication Protocol

JSON-based protocol over TCP sockets (port 9877):

// Request
{"type": "command_name", "params": { ... }}

// Response
{"status": "success", "result": { ... }}

Architecture

Claude AI <-> MCP Server (Python/FastMCP) <-> Ableton Remote Script (Python)
                    |                              |
              Port 9877 TCP                   Ableton Live API (LOM)

REST API (FastAPI) <-> Ableton Remote Script
       |
  Port 8000 HTTP

Max for Live Device <-> LLM Provider API (Ollama/OpenAI/Claude/Groq)
       |
  Node for Max (JavaScript)

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Credits

  • Original AbletonMCP by Siddharth
  • Extended with 200+ tools, REST API, M4L device, and AI helpers

Disclaimer

This is a third-party integration and not made by Ableton.

License

MIT License - See LICENSE file for details.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选