REAPER MCP Server
A Model Context Protocol server that enables AI agents to create fully mixed and mastered tracks in REAPER DAW, supporting project management, MIDI composition, audio recording, and mixing automation.
README
REAPER MCP Server
A comprehensive Model Context Protocol (MCP) server that enables AI agents to create fully mixed and mastered tracks in REAPER with both MIDI and audio capabilities.
Features
- Complete project management (creation, saving, rendering)
- Track operations (creation, routing, parameter adjustment)
- MIDI composition and editing
- Audio recording and importing
- Virtual instrument and effect management
- Mixing and automation
- Mastering tools
- Audio analysis and feedback
Requirements
- REAPER DAW installed
- Python 3.8+
- OSC support enabled in REAPER (for OSC mode)
- ReaScript API enabled in REAPER (for ReaScript mode)
Installation
# Clone the repository
git clone https://github.com/itsuzef/reaper-mcp.git
cd reaper-mcp
# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the package
pip install -e .
Usage
Quick Start
The easiest way to get started is to use the provided startup script:
# Start REAPER first
open /Applications/REAPER.app # On macOS
# or start REAPER manually on other platforms
# Then start the MCP server
./scripts/start_reaper_mcp_server.sh # On Unix/Mac
Windows Users
For Windows users, use one of the provided Windows scripts:
# Using Command Prompt (CMD)
scripts\start_reaper_mcp_server.bat
# Using PowerShell
powershell -ExecutionPolicy Bypass -File scripts\start_reaper_mcp_server.ps1
Configuration
By default, the server will use OSC mode, which is more reliable and doesn't require the ReaScript API to be working correctly. You can configure the server using command-line arguments:
# Start in OSC mode (default)
./scripts/start_reaper_mcp_server.sh --mode=osc # Unix/Mac
scripts\start_reaper_mcp_server.bat --mode=osc # Windows CMD
powershell -File scripts\start_reaper_mcp_server.ps1 -mode osc # Windows PowerShell
# Start in ReaScript mode
./scripts/start_reaper_mcp_server.sh --mode=reapy # Unix/Mac
scripts\start_reaper_mcp_server.bat --mode=reapy # Windows CMD
powershell -File scripts\start_reaper_mcp_server.ps1 -mode reapy # Windows PowerShell
# Configure OSC settings (Unix/Mac)
./scripts/start_reaper_mcp_server.sh --host=192.168.1.110 --send-port=8000 --receive-port=9000
# Configure OSC settings (Windows CMD)
scripts\start_reaper_mcp_server.bat --host=192.168.1.110 --send-port=8000 --receive-port=9000
# Configure OSC settings (Windows PowerShell)
powershell -File scripts\start_reaper_mcp_server.ps1 -host "192.168.1.110" -sendPort 8000 -receivePort 9000
# Enable debug logging
./scripts/start_reaper_mcp_server.sh --debug # Unix/Mac
scripts\start_reaper_mcp_server.bat --debug # Windows CMD
powershell -File scripts\start_reaper_mcp_server.ps1 -debug # Windows PowerShell
Setting up REAPER for OSC
- Open REAPER
- Go to Preferences > Control/OSC/web
- Click "Add" and select "OSC (Open Sound Control)"
- Configure the following settings:
- Device name: ReaperMCP
- Mode: Local port
- Local listen port: 8000
- Local IP: 127.0.0.1 (or your computer's IP address)
- Allow binding messages to REAPER actions and FX learn: Checked (optional)
- Outgoing max packet size: 1024
- Wait between packets: 10ms
Setting up REAPER for ReaScript
- Open REAPER
- Go to Preferences > Plug-ins > ReaScript
- Make sure "Enable Python for ReaScript" is checked
- Set the Python DLL/dylib path to your Python installation
- On macOS:
/opt/homebrew/Cellar/python@3.x/3.x.x/Frameworks/Python.framework/Versions/3.x/Python - On Windows:
C:\Path\to\Python\python3x.dll
- On macOS:
- Run the setup script:
python scripts/setup_reaper_python.py
Project Structure
src/reaper_mcp/: Main package directory__main__.py: Command-line interfaceosc_server.py: OSC-based server implementationserver.py: ReaScript-based server implementation
examples/: Example scripts demonstrating usagescripts/: Utility scripts for setup and running
MCP Tools
The server provides the following MCP tools:
create_project: Creates a new REAPER projectcreate_track: Creates a new track in the current projectlist_tracks: Lists all tracks in the current projectadd_midi_note: Adds a MIDI note to a trackget_project_info: Gets information about the current project
Troubleshooting
ReaScript API Issues
If you're experiencing issues with the ReaScript API, try using the OSC mode instead:
./scripts/start_reaper_mcp_server.sh --mode=osc
OSC Communication Issues
Make sure REAPER is configured correctly for OSC:
- Check that the OSC settings in REAPER match the server settings
- Verify that no firewall is blocking the communication
- Try using the local IP address (127.0.0.1) instead of a network IP
Windows-Specific Troubleshooting
If you're having issues running the MCP server on Windows:
-
Script Execution Issues:
- For PowerShell scripts, you may need to adjust the execution policy:
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser - Alternatively, use the
-ExecutionPolicy Bypassflag as shown in the examples
- For PowerShell scripts, you may need to adjust the execution policy:
-
Path Issues:
- Ensure the REAPER path in the scripts matches your installation location
- Default is
C:\Program Files\REAPER\reaper.exe, modify if needed
-
Virtual Environment:
- If you created the venv with a different method, the activation script might be in a different location
- Try activating manually before running:
venv\Scripts\activate
-
Firewall Blocking:
- Windows Firewall may block OSC communication
- Add exceptions for Python and REAPER in Windows Firewall settings
-
Administrator Rights:
- Try running the Command Prompt or PowerShell as Administrator if you encounter permission issues
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。