strudel-ai

strudel-ai

Enables AI agents to create and edit Strudel music code, render offline WAV audio, and obtain structured hearing reports with waveform, spectrogram, BPM, and onset analysis.

Category
Visit Server

README

strudel-ai

Local HTTP + MCP tool for AI agents to write/edit Strudel code, offline-render WAV audio, and get a structured “hearing” report (waveform, spectrogram, dB envelopes, bands, onsets, estimated BPM).

Sibling project to cryptid-crawler — finished sounds can be copied into the game later.

License: AGPL-3.0-or-later (inherits from Strudel / superdough).

Quick start

cd ~/Projects/strudel-ai
npm install
npm run smoke          # render + analyze a tiny pattern
npm start              # HTTP on http://127.0.0.1:8787
npm run mcp            # MCP stdio server for Cursor

Agent loop

  1. POST /sessions → create session
  2. PUT /sessions/:id/code → write Strudel
  3. POST /sessions/:id/render-analyze → WAV + hearing report
  4. Read hearing.summary / artifacts; PATCH /sessions/:id/code to edit
  5. GET /sessions/:id/diff?from=1&to=2 → code + metric deltas

Same ops exist as MCP tools: session_create, code_set, code_patch, render_analyze, hearing_get, session_diff, artifact_paths, …

HTTP surface

Method Path Purpose
GET /health liveness
POST /sessions create
GET /sessions list
GET /sessions/:id meta
PUT /sessions/:id/code new full revision
PATCH /sessions/:id/code search/replace or unified diff
GET /sessions/:id/code read code
POST /sessions/:id/render offline WAV
POST /sessions/:id/analyze hearing pack
POST /sessions/:id/render-analyze both
GET /sessions/:id/revisions/:n/hearing JSON report
GET /sessions/:id/revisions/:n/artifacts/:name png/wav/json
GET /sessions/:id/diff?from=&to= code + hearing delta
POST /sessions/:id/open open Strudel.cc REPL + play WAV (mpv/xdg-open)

Pass "open": true on render-analyze to do that automatically when finished.

# CLI: open code in Strudel editor + play media
npm run open -- out/ps1_pistol.strudel.js out/ps1_pistol.wav
npm run open -- <sessionId>

Example

SID=$(curl -s -X POST http://127.0.0.1:8787/sessions -H 'content-type: application/json' -d '{"title":"demo"}' | jq -r .id)

curl -s -X PUT http://127.0.0.1:8787/sessions/$SID/code \
  -H 'content-type: application/json' \
  -d '{"code":"note(\"c3 e3 g3 c4\").s(\"sawtooth\").gain(0.4)"}' | jq .currentRevision

curl -s -X POST http://127.0.0.1:8787/sessions/$SID/render-analyze \
  -H 'content-type: application/json' \
  -d '{"cycles":2,"cps":0.5}' | jq '.hearing.summary'

Cursor MCP config

Add to your MCP settings (stdio):

{
  "mcpServers": {
    "strudel-ai": {
      "command": "npx",
      "args": ["tsx", "src/cli.ts", "mcp"],
      "cwd": "/home/agbowman99/Projects/strudel-ai"
    }
  }
}

Notes

  • Default sample bank is github:tidalcycles/dirt-samples (override with STRUDEL_AI_SAMPLES). Synths (sawtooth, sine, …) come from superdough.
  • @kabelsalat/web is patched on postinstall so Node can import SalatRepl.
  • Session data lives in ./sessions/ (gitignored).
  • Architecture diagram: mermaid-lite project Strudel AI (ml show "Strudel AI").

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured