RhymeBook
An AI-powered creative studio for writing lyrics, finding beats, and tracking recording sessions, integrating with AI assistants via the Model Context Protocol.
README
<p align="center"> <img src="./assets/rhymebook_logo.jpeg" alt="RhymeBook Logo" width="400"> </p>
<h1 align="center">π€ RhymeBook - Music Artist MCP App</h1>
<p align="center"> Your AI-powered creative studio for writing lyrics, finding beats, and tracking sessions.<br> <strong>40+ tools</strong> to supercharge your music workflow β from rhyme schemes to vocal separation. </p>
<p align="center"> <img src="https://img.shields.io/badge/Node.js-18+-339933?style=flat&logo=node.js&logoColor=white" alt="Node.js"> <img src="https://img.shields.io/badge/TypeScript-5.0+-3178C6?style=flat&logo=typescript&logoColor=white" alt="TypeScript"> <img src="https://img.shields.io/badge/MCP-Protocol-FF6B6B?style=flat" alt="MCP"> <img src="https://img.shields.io/badge/SQLite-Database-003B57?style=flat&logo=sqlite&logoColor=white" alt="SQLite"> </p>
<p align="center"> <img src="https://img.shields.io/badge/version-1.0.0-blue?style=flat" alt="Version"> <img src="https://img.shields.io/badge/license-MIT-green?style=flat" alt="License"> <img src="https://img.shields.io/badge/tools-40+-orange?style=flat" alt="Tools"> <img src="https://img.shields.io/badge/bundle-634KB-brightgreen?style=flat" alt="Bundle Size"> <img src="https://img.shields.io/badge/tests-78%20passing-brightgreen?style=flat" alt="Tests"> </p>
<p align="center"> <a href="https://github.com/cavanaughdesign/rhymebook-mcp-server">β Star on GitHub</a> β’ <a href="https://github.com/cavanaughdesign/rhymebook-mcp-server/issues">π Report Bug</a> β’ <a href="https://github.com/cavanaughdesign/rhymebook-mcp-server/issues">π‘ Request Feature</a> </p>
π― What is RhymeBook?
RhymeBook is an AI-powered music production assistant that lives inside your favorite AI tools (Claude Desktop, VS Code, and more). It combines powerful lyric writing tools, beat management, and session tracking into one seamless workflow.
Why Artists Love It
| π€ Write Better | π§ Find Perfect Beats | π Stay Organized |
|---|---|---|
| AI rhyme finder with slant & multi-syllable matches | Filter by genre, mood, BPM, and energy | Track every session, take, and collaborator |
| Real-time syllable counting & flow analysis | Match lyrics to beats using AI | Visual progress from writing β released |
| Export to text, markdown, JSON, or LRC | Waveform visualization & audio effects | Persistent SQLite database |
π Powered by Model Context Protocol
RhymeBook uses MCP to give AI assistants direct access to your music tools. Ask Claude to find rhymes, log a take, or browse beats β it all happens instantly through natural conversation.
π€ Claude Skill Included
RhymeBook comes with a built-in Claude skill that provides intelligent assistance:
- Smart Tool Selection - Automatically picks the right tool for your request
- Creative Partner - Proactively suggests rhymes, flow improvements, and beat matches
- Workflow Guidance - Guides you through writing, recording, and production
- Natural Language - Just ask naturally, no need to remember tool names
The skill is located in .claude/skills/SKILL.md and activates automatically when you mention music-related terms.
β¨ Features
π Dashboard
- Overview Stats - Total songs, sessions, takes, beats, collaborators
- Song Progress Funnel - Visual pipeline from writing to released
- Weekly Activity Chart - 8-week trend visualization
- Activity Feed - Real-time feed of all actions with filtering
- Insights - Most productive day, avg session length, completion rate
- Recent Items - Quick access to recent songs and sessions
- Quick Actions - One-click access to common tasks
- Beat Library Stats - Overview of beat collection
π΅ Lyric Lab
- Rhyme Finder - Find perfect, slant, and multi-syllable rhymes
- Syllable Counter - Live syllable counting per line
- Flow Visualizer - Visual representation of rhythm patterns
- Thesaurus - Contextual word suggestions
- Section Organizer - Manage verses, choruses, bridges, and more
- Save & Export - Export lyrics in text, markdown, JSON, or LRC formats
- Import Lyrics - Import from TXT, JSON, LRC, or SRT files
- Batch Import/Export - Process multiple files at once
ποΈ Session Tracker
- Project Dashboard - Overview of all songs in progress
- Take Manager - Log and rate recording takes (1-5 stars)
- Collaboration Tracker - Manage features, producers, engineers
- Milestone Progress - Visual progress bars (writing β recording β mixing β mastering)
- Notes & Feedback - Attach notes to sessions
- Persistent Storage - All data saved to SQLite database
π§ Beat Explorer
- Browse & Filter - Filter by genre, mood, BPM, energy level
- Wavesurfer.js Waveform - Professional waveform visualization
- Frequency Visualizer - Live frequency bars during playback
- Audio Player - Full playback controls with seek, volume
- Audio Effects - Reverb, delay, distortion, and 3-band EQ (Tone.js)
- Scrub Bar - Interactive progress bar with drag-to-seek
- Auto BPM/Key Detection - music-metadata analyzes audio files
- Favorites & Collections - Organize beats into playlists
- Lyric-to-Beat Matcher - AI suggests beats matching your lyrics' energy
- Library Management - Set custom folder path for beat files
- Auto-Import - Scan and import beats from your library folder
- Copy to Library - Add beats from anywhere to your library
- Vocal Separation - Spleeter AI for stem extraction
β‘ Performance & Security
Performance Optimizations
- Async File Operations - All file I/O is non-blocking
- Database Indexes - Optimized queries for common operations
- Parallel Dashboard Queries - Faster dashboard loading
- Scan Caching - Beat library scans cached for 1 minute
- Real-time Vocal Removal - No playback restart needed
- Dynamic Library Loading - Tone.js and Wavesurfer.js loaded on-demand
- Optimized Bundle Size - 634KB single-file bundle (under 5MB MCP limit)
- Tree Shaking - Unused code automatically removed
- Terser Minification - Production code compressed and optimized
Security Features
- Path Traversal Protection - Validates all file paths
- Rate Limiting - 100 requests per 15 minutes
- CORS Configuration - Environment-based origin allowlist
- Input Validation - Zod schemas with length limits
- Graceful Shutdown - Proper cleanup handlers
π Quick Start
Prerequisites
- Node.js 18+
- npm or pnpm
- FFmpeg (for audio processing)
- Spleeter (for vocal separation)
Installing FFmpeg
Windows (Chocolatey):
choco install ffmpeg
Windows (Manual):
- Download from ffmpeg.org
- Add to PATH environment variable
macOS (Homebrew):
brew install ffmpeg
Linux (Ubuntu/Debian):
sudo apt update && sudo apt install ffmpeg
Installing Spleeter
Via pip:
pip install spleeter
Via conda:
conda install -c conda-forge spleeter
Note: Spleeter requires Python 3.7+ and will download AI models on first use (~265MB).
# Clone the repository
git clone https://github.com/yourusername/rhymebook-mcp-server.git
cd rhymebook-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
Running the Server
HTTP Mode (for web-based hosts)
npm start
# Server runs on http://localhost:3001
# MCP endpoint: http://localhost:3001/mcp
Stdio Mode (for Claude Desktop)
npm run start:stdio
Development Mode
npm run dev
# Runs both server and UI in watch mode
π Project Structure
rhymebook-mcp-server/
βββ src/
β βββ server/
β β βββ index.ts # MCP server entry point
β βββ tools/
β β βββ lyric-lab.ts # Lyric Lab tools (9 tools)
β β βββ session-tracker.ts # Session Tracker tools (10 tools)
β β βββ beat-explorer.ts # Beat Explorer tools (14 tools)
β β βββ dashboard.ts # Dashboard tools (4 tools)
β βββ db/
β β βββ database.ts # SQLite database setup
β β βββ operations.ts # Database CRUD operations
β β βββ beats-library.ts # Beat library file management
β β βββ lyrics-io.ts # Lyrics import/export
β βββ ui/
β βββ index.html # Main HTML template
β βββ styles.css # UI styles (dark theme)
β βββ main.ts # Client-side logic
β βββ audio-engine.ts # Web Audio API engine
β βββ visualizers.ts # Waveform & frequency visualizers
β βββ beat-player.ts # Beat player component
βββ dist/
β βββ server/ # Compiled server code
β βββ ui/
β βββ index.html # Bundled single-file UI
βββ claude_desktop_config.example.json # Example Claude Desktop config
βββ CONFIGURATION.md # Detailed configuration guide
βββ package.json
βββ tsconfig.json
βββ tsconfig.server.json
βββ vite.config.ts
π οΈ Available Tools
Lyric Lab Tools
| Tool | Description |
|---|---|
find-rhymes |
Find perfect, slant, and multi-syllable rhymes |
count-syllables |
Count syllables in lyrics |
analyze-flow |
Analyze rhythm and flow patterns |
get-synonyms |
Get contextual synonyms |
save-lyrics |
Save lyrics to database |
export-lyrics |
Export lyrics (text, markdown, JSON, LRC) |
import-lyrics |
Import lyrics from file or text |
batch-import-lyrics |
Import all lyrics from a directory |
get-all-songs |
Get all saved songs |
Session Tracker Tools
| Tool | Description |
|---|---|
get-project-dashboard |
Get overview of all songs |
get-recording-sessions |
Get recording sessions |
log-take |
Log a new recording take |
get-collaborators |
Get all collaborators |
update-song-progress |
Update song status and progress |
add-session-note |
Add notes to a session |
create-song |
Create a new song project |
create-session |
Schedule a recording session |
add-collaborator |
Add a new collaborator |
Beat Explorer Tools
| Tool | Description |
|---|---|
browse-beats |
Browse and filter beats |
get-beat-details |
Get detailed beat information |
toggle-favorite |
Add/remove from favorites |
get-collections |
Get all beat collections |
add-to-collection |
Add beat to collection |
create-collection |
Create a new collection |
match-lyrics-to-beat |
Find beats matching lyrics |
get-beat-stats |
Get library statistics |
add-beat |
Add a new beat (auto-detects BPM/key) |
analyze-audio |
Analyze audio file for BPM, key, duration |
Audio Processing Tools
| Tool | Description |
|---|---|
separate-audio |
Separate audio into stems using Spleeter AI |
extract-vocals |
Extract vocals from a track |
check-audio-tools |
Check available audio processing tools |
Library Management Tools
| Tool | Description |
|---|---|
get-library-path |
Get current beats library path |
set-library-path |
Set beats library folder path |
scan-library |
Scan library for audio files |
import-beats |
Import new beats from library |
copy-beat-to-library |
Copy beat file to library |
Dashboard Tools
| Tool | Description |
|---|---|
get-dashboard-summary |
Get comprehensive overview of all data |
get-recent-activity |
Get activity feed with filtering |
get-progress-stats |
Get detailed progress statistics |
get-quick-stats |
Get quick stats for widgets |
π¨ UI Features
- Dark Theme - Easy on the eyes for late-night sessions
- Responsive Design - Works on desktop and tablet
- Real-time Updates - Instant feedback as you type
- Toast Notifications - Clear feedback for actions
- Modal Dialogs - Clean export interface
- Drag & Drop - Reorder song sections
- Keyboard Shortcuts - Ctrl+S (save), Ctrl+N (new), Space (play/pause), Escape (close modal)
- Auto-Save - Automatic save after 30 seconds of inactivity
- Loading States - Visual feedback during async operations
π€ Vocal Removal
RhymeBook includes real-time vocal removal for practicing and remixing:
- Center Channel Extraction - Removes centered vocals from stereo tracks
- Real-time Adjustment - Smooth slider control with no audio glitches
- Frequency Filtering - Attenuates vocal frequency ranges (250Hz - 3.5kHz)
How to Use
- Load a beat in the Beat Explorer
- Use the π€ Vocals slider in the player controls
- Slide right to reduce vocals (0% = original, 100% = maximum removal)
Best Results
- β Stereo tracks with centered vocals
- β Modern pop/hip-hop productions
- β οΈ Older stereo mixes (moderate results)
- β Mono tracks (no stereo information to extract)
πΎ Database
RhymeBook uses SQLite for persistent storage. The database is automatically created at:
- Windows:
%USERPROFILE%\.rhymebook\rhymebook.db - Mac/Linux:
~/.rhymebook/rhymebook.db
Database Schema
| Table | Description |
|---|---|
songs |
Song projects with title, status, progress, notes |
song_sections |
Lyrics organized by section type (verse, chorus, etc.) |
collaborators |
Artists, producers, engineers, writers |
song_collaborators |
Many-to-many relationship between songs and collaborators |
recording_sessions |
Studio session tracking with date, studio, engineer |
takes |
Individual recording takes with ratings (1-5 stars) |
beats |
Beat library with BPM, key, energy, file path |
beat_genres |
Genre tags for beats (many-to-many) |
beat_moods |
Mood tags for beats (many-to-many) |
beat_tags |
Custom tags for beats |
collections |
Named beat playlists |
collection_beats |
Beats in collections with position |
settings |
App configuration (library path, theme) |
Database Indexes
Optimized indexes for common queries:
- Songs by status and update date
- Sessions by date and song
- Takes by session and timestamp
- Beats by favorite status, BPM, and energy
π Beats Library Management
Setting Your Library Path
Use the set-library-path tool to point to your beats folder:
Set library path: C:\Users\You\Music\Beats
Supported Audio Formats
- MP3, WAV, FLAC, AAC, OGG, M4A, WMA
Auto-Import Beats
- Set your library path
- Run
scan-libraryto see all audio files - Run
import-beatsto add them to the database
Filename Parsing
RhymeBook automatically extracts info from filenames:
Beat Name 140BPM Am.mp3β Title: "Beat Name", BPM: 140, Key: AmDark_Trap_150_Cm.wavβ Title: "Dark Trap", BPM: 150, Key: Cm
βοΈ Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
PORT |
HTTP server port | 3001 |
ALLOWED_ORIGINS |
Comma-separated CORS origins | http://localhost:3000,http://localhost:3001,http://localhost:5173 |
Claude Desktop Configuration
Add to your claude_desktop_config.json:
Windows:
{
"mcpServers": {
"rhymebook": {
"command": "node",
"args": ["C:\\Users\\YourUsername\\path\\to\\rhymebook-mcp-server\\dist\\server\\index.js", "--stdio"]
}
}
}
macOS/Linux:
{
"mcpServers": {
"rhymebook": {
"command": "node",
"args": ["/Users/yourusername/path/to/rhymebook-mcp-server/dist/server/index.js", "--stdio"]
}
}
}
With Environment Variables:
{
"mcpServers": {
"rhymebook": {
"command": "node",
"args": ["/path/to/rhymebook-mcp-server/dist/server/index.js", "--stdio"],
"env": {
"PORT": "3001"
}
}
}
}
VS Code Configuration
Add to your VS Code settings.json:
{
"mcp.servers": {
"rhymebook": {
"command": "node",
"args": ["${workspaceFolder}/dist/server/index.js", "--stdio"]
}
}
}
HTTP Mode (for web-based hosts)
{
"mcpServers": {
"rhymebook-http": {
"url": "http://localhost:3001/mcp"
}
}
}
π For detailed configuration instructions, see CONFIGURATION.md
π Usage Examples
Finding Rhymes
User: Find rhymes for "flow"
Assistant: [Calls find-rhymes tool]
Result: Perfect: go, show, know, grow...
Slant: soul, roll, control...
Multi: overflow, undertow...
Matching Lyrics to Beats
User: I have aggressive lyrics about hustling, find me a beat
Assistant: [Calls match-lyrics-to-beat with lyrics]
Result: Suggested beats ranked by energy/mood match
Tracking Recording Sessions
User: Log take 4 for today's session - 5 stars, best take!
Assistant: [Calls log-take tool]
Result: Take logged, marked as best take
Getting Dashboard Overview
User: Show me my project dashboard
Assistant: [Calls get-dashboard-summary tool]
Result: Overview stats, recent activity, insights
Vocal Removal
User: Play this beat with vocals removed
Assistant: [Loads beat in player, sets vocal removal to 100%]
Result: Instrumental version plays
πΊοΈ Roadmap
- [ ] SoundCloud integration for beat discovery
- [ ] Spotify playlist sync
- [ ] AI-powered lyric suggestions
- [ ] Collaborative sessions with real-time sync
- [ ] Mobile companion app
- [ ] Export to DAW formats (MIDI, stems)
π€ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Development Setup
# Clone your fork
git clone https://github.com/yourusername/rhymebook-mcp-server.git
cd rhymebook-mcp-server
# Install dependencies
npm install
# Run tests
npm test
# Start development server
npm run dev
π License
This project is licensed under the MIT License - see the LICENSE file for details.
π€ Author
Anthony M Cavanaugh (he/him)
- Company: Cavanaugh Design Studio
- GitHub: @cavanaughdesign
- Email: cavanaughdesign@gmail.com
- Twitter/X: @cavanaughdesign
- Instagram: @cavanaughdesignstudio
π Acknowledgments
- Built with Model Context Protocol
- UI powered by MCP Apps SDK
- Audio processing with Tone.js and Wavesurfer.js
- Database powered by Better-SQLite3
- Inspired by the creative process of music artists everywhere
<p align="center"> <strong>Made with π€ by <a href="https://cavanaughdesignstudio.com">Cavanaugh Design Studio</a></strong><br> <em>For artists who rap, write, and create</em> </p>
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.