Luminous MCP Server
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., "@Luminous MCP Serverfind my most-played jazz tracks from the 90s under 120 BPM"
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.
Luminous MCP Server
A Model Context Protocol (MCP) server for Luminous Music Player.
Connects your AI assistants (Claude Desktop, Antigravity, Cursor, Zed, Ollama) to your local music library.

Features
Library Search & Filtering: Search tracks, albums, artists, genres, composers, and lyrics using SQLite FTS5. Filter by BPM, LUFS loudness, dynamic range, and bit depth.
Listening Analytics: Inspect play counts, skip rates, top tracks/artists, and forgotten favorites.
Playlist Management: Query, generate, and populate static and dynamic playlists.
Metadata Hygiene: Audit library for missing tags (album art, composer, year, lyrics) and assist in custom genre taxonomy assignment.
Playback Control: Interact with running Luminous instances for transport controls (play, pause, next/prev, seek, volume, shuffle, repeat) and queue replacement.
Real-Time UI State Sync: Non-blocking loopback notifications automatically signal running desktop instances to update playlist views immediately upon MCP mutations.
Related MCP server: Music Collection MCP Server
Example Prompts
Here are prompt examples demonstrating natural language queries you can ask your AI assistant:
Playback & Transport Control
"What is currently playing right now in Luminous?"
"Play track 'Strobe' by deadmau5 now."
"Pause playback."
"Set volume to 50%."
"Skip to the next song."
"Seek forward to 2 minutes 15 seconds."
"Turn on shuffle and set repeat mode to all."
"Replace the current queue with these tracks and begin playback."
Music Discovery & Acoustic Filtering
"Look up the track details and audio specs for my song 'Heartbeat Highway' by Cannons."
"Find all songs by Def Leppard on my 'Hysteria' album, including their release years and play counts."
"Search my library for electronic or synthwave tracks released between 2020 and 2026."
"Find quiet ambient or folk songs with an integrated loudness lower than -14 LUFS (like my Danheim collection) for evening relaxation."
Listening Habits & Analytics Insights
"What are my top 5 most listened to artists in my library and what are my total play counts for each?"
"Surface some forgotten favorites: tracks I used to listen to frequently that haven't been played in the last few months."
"Which tracks in my library have the highest skip count or skip ratio?"
"Show me my recent listening history from today, including playback context and duration."
Artist Catalog & Collaborations
"Give me an artist summary for Cannons: how many tracks and albums do I own, who are their composers/producers, and what are my top played songs by them?"
"Summarize my Danheim catalog: total tracks, albums, and genre distribution."
"What albums do I have by Shania Twain, and which of her tracks have I played the most?"
Playlist Creation & Curation
"Inspect my 'Late Night Mix' or 'Road Trip' playlist and show me the tracks and running order."
"Create a new playlist called 'Indie & Synth Gems' and populate it with 10 tracks by Cannons and similar electronic/alternative artists in my library."
"Find my top 10 most played Country and Southern Rock tracks (like Ella Langley or Brothers Osborne) and add them to a new playlist named 'Country Favorites'."
"List all of my current playlists and how many tracks each one contains."
Metadata Hygiene & Library Auditing
"Audit my library for missing metadata: how many tracks are missing genres, release years, or album art?"
"Check which songs in my library are missing MusicBrainz recording or track IDs."
"Find tracks in my library with compound genre tags (like 'Metal; Progressive Metal' or 'Ambient; Ambient Folk') so I can review my taxonomy."
Token Efficiency & Optimization
Luminous MCP implements strict token-efficiency and context window optimization best practices designed specifically for LLMs:
Optimization Feature | Implementation | Token & Context Window Impact |
Compact JSON Serialization | Stripped indentation whitespace by default ( | 15%–25% reduction across all tool responses |
Sparse Field Pruning | Recursively strips | 25%–35% reduction across metadata-dense inspection tools |
On-Demand Lyrics Gating | Full song lyrics gated behind explicit | 500–1,500+ tokens saved per track lookup |
Search Detail Levels |
| 50%–70% reduction on search listings |
Metric Deduplication | Canonical ISO 8601 timestamps ( | 15%–20% reduction on analytics and history queries |
Bounded Collections | Caps artist summary entity lists ( | Prevents 1,000–3,000+ token explosions on prolific artists |
Offset Pagination | Incremental | Eliminates redundant page re-fetching during multi-turn exploration |
Getting Started
Prerequisites
Bun (v1.1+)
Luminous Music Player installed with a music library scanned
Installation
git clone https://github.com/esoltys/luminous-mcp.git
cd luminous-mcp
bun install
bun run buildRunning the Server
bun run startOne-Click Install (Claude Desktop)
Install directly via the official MCP Bundle (.mcpb) format:
Build the bundle:
bun run package:mcpbOpen Claude Desktop, go to Settings > Extensions, and drag
dist/luminous-mcp.mcpbinto the window.Click Install. The extension runs a self-contained binary with zero external dependencies.
Manual Configuration (Claude Desktop, Antigravity, Cursor)
Alternatively, add luminous to your claude_desktop_config.json or MCP client configuration:
{
"mcpServers": {
"luminous": {
"command": "bun",
"args": ["run", "C:/path/to/luminous-mcp/src/index.ts"]
}
}
}Development
Typecheck:
bun run typecheckTests:
bun testBuild:
bun run build
License
MIT © Eric James Soltys
This server cannot be deployed
Maintenance
Related MCP Connectors
The media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
Audio features + harmonic set-building for tracks by name/ISRC. Spotify audio-features replacement.
Accurate anime-song (anison) database for AI-built playlists — export to Spotify/Apple/YT Music
Search speech in podcasts, government meetings, and your own audio: speakers, entities, timestamps.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceAnalyze listening patterns, create custom playlists, discover missing albums, validate radio streams, and provide personalized recommendations through natural language.49 npm89AGPL 3.0
- FlicenseNot gradedqualityDmaintenanceProvides intelligent access to local music collections through advanced metadata management, album classification across 8 types, collection analytics, and smart search capabilities for AI-powered music library organization.14-
- AlicenseAqualityDmaintenanceConnects AI assistants to a self-hosted Your Spotify instance and Spotify's Web API for deep listening analytics and playback control. It enables users to query unlimited listening history, generate custom Wrapped summaries, and manage playlists through natural language.18Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables music search, metadata retrieval, local audio analysis (tempo, key, energy), recommendations, song recognition, and classical work resolution via Spotify, Last.fm, AudD, MusicBrainz, and Songkick APIs.-