sonic-mcp
MCP server that connects Claude Code to Sonic Pi for AI-assisted beat making, enabling live code execution and pattern management.
README
sonic-mcp
MCP server that connects Claude Code to Sonic Pi for AI-assisted beat making.
Requirements
Setup
1. Add to Claude Code
Add this to ~/.claude/mcp.json for global use, or a project's .mcp.json to keep it scoped:
{
"mcpServers": {
"sonic-pi": {
"command": "uvx",
"args": ["--from", "git+https://github.com/AJBogo9/sonic-mcp.git", "sonic-mcp"],
"env": {
"SONIC_PI_PATTERNS_DIR": "/home/yourname/patterns"
}
}
}
}
SONIC_PI_PATTERNS_DIR defaults to ~/patterns if not set.
2. Start the Sonic Pi listener
Paste this into a Sonic Pi buffer and hit Run before using any MCP tools. It listens for incoming code over OSC and evaluates it live:
live_loop :mcp_runner do
use_real_time
code = sync "/osc*/run-code"
begin
eval(code[0].to_s)
rescue Exception => e
puts "Error: #{e.message}"
end
end
That's it. You can now ask Claude to write and play Sonic Pi code directly.
Tools
| Tool | Description |
|---|---|
run_code |
Send Sonic Pi code to execute |
stop_all |
Stop all playing sounds |
get_log |
Read Sonic Pi's output log so Claude can see errors and self-correct |
save_pattern |
Save a pattern to the library |
list_patterns |
List patterns in the library |
load_pattern |
Load a pattern as a starting point for iteration |
record_start |
Start Sonic Pi's built-in recording |
record_stop |
Stop recording and save to disk |
How it works
Claude Code calls tools over the MCP protocol. The server translates each tool call into an OSC message sent to Sonic Pi on localhost:4560. The get_log tool reads ~/.sonic-pi/log/server-output.log so Claude can catch errors and fix them without you needing to copy-paste them.
Local development
git clone https://github.com/yourusername/sonic-mcp.git
cd sonic-mcp
pip install -e .
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.