sonicpi-mcp
Uses OpenAI's API to convert natural language requests into Sonic Pi code for music generation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@sonicpi-mcpcreate a rock drum beat"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Sonic Pi MCP Server
A local MCP server that controls Sonic Pi via OSC with AI-powered music generation.
How It Works
MCP Server receives natural language requests
AI Generator converts requests to Sonic Pi code (patterns or OpenAI)
OSC Client sends code to Sonic Pi via OSC
Sonic Pi executes the code and plays music
Related MCP server: SuperCollider MCP Server
Setup
1. Install Dependencies
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -e .2. Configure Sonic Pi
Add this code to Sonic Pi and click "Run":
live_loop :mcp_listener do
use_real_time
code_message = sync "/osc*/mcp/code"
begin
eval(code_message[0])
rescue => e
puts "Error executing code: #{e.message}"
end
end3. Optional: Add OpenAI API Key
cp .env_example .env
# Edit .env and add: OPENAI_API_KEY=your-key-here4. Run Server
python -m sonicpi_mcpUsage
Via Cursor (Recommended)
Ensure server is running
Use commands like: "create a rock beat", "make techno music", "play jazz piano"
Via Command Line
# Create and play music
echo '{"tool": "create_and_play", "args": {"request": "create a rock drum beat"}}' | python3 -m sonicpi_mcp
# Run Sonic Pi code directly
echo '{"tool": "run_code", "args": {"source": "play 60, amp: 2"}}' | python3 -m sonicpi_mcp
# Set BPM
echo '{"tool": "set_bpm", "args": {"bpm": 120}}' | python3 -m sonicpi_mcp
# Stop all
echo '{"tool": "stop_all", "args": {}}' | python3 -m sonicpi_mcpAvailable Tools
create_and_play- Generate and play music from natural languagerun_code- Execute Sonic Pi code directlyset_bpm- Set tempostop_all- Stop all audiocue- Send cue messagesgenerate_music- Generate code without playinglist_patterns- Show available patternsget_pattern- Get specific patterntail_logs- View recent logsdiagnose- Check connection status
Troubleshooting
No sound? Ensure the Sonic Pi listener live_loop is running.
Port issues? Server auto-discovers Sonic Pi's port. Check with: echo '{"tool": "diagnose", "args": {}}' | python3 -m sonicpi_mcp
OSC not working? Check Sonic Pi's Network settings and enable "Allow incoming OSC messages".
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Producer/Riffusion AI music generation
Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.
AI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.0 and more.
AI music and podcast platform for autonomous agents. SoundCloud for AI bots.
Related MCP Servers
- AlicenseDqualityDmaintenanceA Model Context Protocol server that allows AI assistants like Claude and Cursor to create music and control Sonic Pi programmatically through OSC messages.211 npm18MIT
- FlicenseAqualityDmaintenanceEnables AI assistants to generate and control real-time audio synthesis through natural language descriptions using SuperCollider. Features 10 built-in synth types, pattern sequencing, audio recording, and server lifecycle management for creating sounds from simple English descriptions.111-
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to control synthesizer parameters in real-time by translating natural language commands into OSC messages sent to a JUCE synthesizer application.-
- AlicenseNot gradedqualityDmaintenanceEnables natural language control of OSC (OpenSoundControl) messages, allowing users to generate, interpret, validate, and debug OSC messages through an LLM interface for parametric control of multimedia devices.3MIT