Lyrion MCP Server
Enables LLMs to control a Lyrion Music Server (LMS/Squeezebox) for playback, search, library browsing, and player management.
README
Lyrion MCP Server
An MCP server that lets LLMs control a Lyrion Music Server (LMS / Squeezebox) instance.
Features
- 9 MCP tools (optimized for context efficiency — ~1,400 tokens of definition overhead)
- Play by URL, track ID, search, collection ID, or Spotify Artist Radio
- Search across local library + Spotify (via the Spotty plugin)
- Full playback control: pause, stop, seek, power on/off
- Playlist management: add, insert, delete, clear, move, jump, save
- Player settings: volume, shuffle, repeat, mute
- Player sync/unsync
- Library browsing: genres, artists, albums, titles, years, playlists
- Raw LMS CLI passthrough for advanced commands
Quick Start
pip install -r requirements.txt
LMS_HOST=your-lms-host python main.py
Configuration
Set environment variables (see .env.example):
| Variable | Default | Description |
|---|---|---|
LMS_HOST |
localhost |
Lyrion server host |
LMS_PORT |
9000 |
Lyrion server port |
LMS_USERNAME |
(none) | LMS username (if auth enabled) |
LMS_PASSWORD |
(none) | LMS password (if auth enabled) |
LMS_HTTPS |
off | Set 1 if LMS uses HTTPS |
MCP_TRANSPORT |
stdio |
stdio, sse, or streamable-http |
MCP_HOST |
0.0.0.0 |
Bind address (HTTP transports) |
MCP_PORT |
8000 |
Port (HTTP transports) |
Docker
docker build -t lyrion-mcp .
docker run -d -p 8000:8000 -e LMS_HOST=your-lms-host lyrion-mcp
The server runs on http://localhost:8000 using the streamable-http
transport. Point your MCP client at that URL.
Tools
| Tool | Description |
|---|---|
get_status |
System topology (all players) or now-playing (with player_id) |
play_media |
Play by URL, track_id, search (defaults to Artist Radio), or collection ID |
search_media |
Search local library + Spotify, return playable URLs |
control_playback |
Pause, stop, play, seek, power on/off |
manage_playlist |
Add, insert, delete, clear, move, jump, save |
set_player |
Volume, shuffle, repeat, mute |
sync_players |
Sync or unsync players |
browse_library |
Browse genres/artists/albums/titles/years/playlists |
query_lms |
Raw LMS CLI passthrough |
Development
pip install -r requirements.txt
python -m pytest -q # 110 tests
python -m mypy client.py main.py
python -m pyflakes client.py main.py tests/
Requirements
- Python 3.12+
- A running Lyrion Music Server (9.x)
- Spotty plugin (optional, for Spotify)
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.