Lyngdorf 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., "@Lyngdorf MCP Server set the volume to -25 dB"
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.
Lyngdorf MCP Server
DISCLAIMER: This project is an independent, community-developed tool and is NOT affiliated with, endorsed by, or supported by Lyngdorf Audio. Use at your own risk. For official Lyngdorf products and support, visit lyngdorf.steinwaylyngdorf.com.
CODE GENERATION: Most of this codebase was generated using Claude Code, Anthropic's AI coding agent. The implementation demonstrates Claude Code's ability to create production-ready software from high-level requirements.
A Model Context Protocol (MCP) server for controlling Lyngdorf Audio devices (TDAI, MP, and CD series) via TCP. Features automatic device discovery, comprehensive control, volume safety, and built-in documentation.

Features
🔍 Auto-Discovery: Automatically finds and connects to Lyngdorf devices on startup
🛡️ Volume Safety: Two-tier safety system (Warning & Hard Limit) to protect your ears and equipment
🧠 Smart Capabilities: Automatically detects device model and prevents unsupported commands (e.g., no streaming on TDAI-2170)
🎵 43 Control Tools: Power, volume, source, RoomPerfect, voicing, tone controls, playback, and streaming
📚 Knowledge Base: Built-in manual data and command references for multiple models
🔄 Auto-Reconnect: Maintains connection with automatic recovery
🌐 Multi-Device: Supports TDAI, MP, and CD series with seamless device switching
Related MCP server: lyrion-mcp
Supported Devices
The server includes specific capability profiles for:
TDAI Series: 1120, 2170, 2190, 2210, 3400
MP Series: 40, 50, 60
CD Series: CD-1
Unknown devices are supported with a generic profile assuming full capabilities.
Installation
Prerequisites
Node.js 22+
npm or yarn
Install from npm
npm install -g lyngdorf-mcpOr use npx without installing:
npx lyngdorf-mcpInstall from Source
git clone <repository-url>
cd lyngdorf-mcp
npm install
cp .env.example .env
npm run buildUsage
With Claude Desktop
Add to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Using npm package (recommended):
{
"mcpServers": {
"lyngdorf": {
"command": "npx",
"args": ["lyngdorf-mcp"],
"env": {
"VOLUME_WARNING_THRESHOLD": "-20",
"VOLUME_HARD_LIMIT": "-10"
}
}
}
}Using local installation:
{
"mcpServers": {
"lyngdorf": {
"command": "node",
"args": ["/absolute/path/to/lyngdorf-mcp/dist/index.js"],
"env": {
"VOLUME_WARNING_THRESHOLD": "-20",
"VOLUME_HARD_LIMIT": "-10"
}
}
}
}Configuration (Environment Variables)
Variable | Default | Description |
| (Auto) | Manually specify device IP if auto-discovery fails |
|
| Volume level (dB) that triggers a warning requiring user confirmation |
|
| Maximum volume level (dB) that cannot be exceeded via tools |
How It Works
On startup, the server:
Auto-discovers all Lyngdorf devices on your network via mDNS
Auto-connects if exactly one device is found
Lists devices if multiple are found (use
listDevicesandselectDevicetools)
No manual configuration needed! Just start Claude Desktop and ask:
"What's my current volume?"
Available Tools (43)
Power Control
powerOn,powerOff,togglePowercheckPowerState- Check if device is active or in standby
Volume Control (Safety Protected)
setVolume- Set volume (with safety checks)volumeUp,volumeDown- Adjust by 0.5dBgetVolume- Get current levelmute,unmute
Audio & Tone
setBass,getBass- Bass gain controlsetTreble,getTreble- Treble gain controlsetBalance,getBalance- L/R BalancesetBassFrequency,getBassFrequencysetTrebleFrequency,getTrebleFrequency
Input & Source
setSource,getSourcelistSources- List all available inputs
RoomPerfect & Voicing
setRoomPerfectFocus,setRoomPerfectGlobal,getRoomPerfectlistRoomPerfectPositions- List available focus positionssetVoicing,nextVoicing,previousVoicing,getVoicinglistVoicings- List available voicing presets
Playback & Streaming (Model Dependent)
play,pause,stop,next,previousgetStreamType- Detect current stream (Spotify, Roon, AirPlay, etc.)
Device Management
discoverDevices,listDevices,selectDevicegetStatus- Comprehensive device status
Available Resources
Access manuals and documentation as MCP resources:
lyngdorf://manual/{model}/commands- Command referencelyngdorf://manual/{model}/owners/index- Owner's Manual TOClyngdorf://manual/{model}/owners/{section}- Specific manual sectionslyngdorf://search?q={query}- Search all manuals
Supported Manuals: TDAI-1120, TDAI-2170, TDAI-2210, TDAI-3400
Troubleshooting
No Devices Found
Ensure device is powered on and connected to the network.
Check if you are on the same subnet.
Try setting
LYNGDORF_IPmanually.
Volume Limit Errors
If you see "Volume -XdB exceeds warning threshold...", simply ask the user for confirmation to proceed, or lower the requested volume.
Development
Run in Development Mode
npm run devTest
npm testCoverage: 125 passing tests covering tools, transport, discovery, and capabilities.
Project Structure
lyngdorf-mcp/
├── src/
│ ├── index.ts # Server entry & discovery
│ ├── tools.ts # Tool definitions & handlers
│ ├── capabilities.ts # Device capability matrix
│ ├── transport.ts # TCP communication
│ └── ...
├── docs/kb/ # JSON Knowledge Base
└── dist/ # Compiled outputLicense
MIT
Disclaimer
This is an independent project developed by the community. It is NOT affiliated with, endorsed by, or supported by Lyngdorf Audio A/S or Steinway Lyngdorf.
Available Tools
43 toolsdiscoverDevicesC
Discover Lyngdorf devices on the network via mDNS
Inputs: timeout.
getAudioStatusB
Get current audio format information
Inputs: no named parameters.
getBalanceB
Get current left/right balance
Inputs: no named parameters.
getBassB
Get current bass gain level
Inputs: no named parameters.
getBassFrequencyC
Get current bass frequency
Inputs: no named parameters.
getDeviceInfoB
Get device model and identification information
Inputs: no named parameters.
getMuteStatusB
Check if audio is currently muted
Inputs: no named parameters.
getRoomPerfectB
Get current RoomPerfect setting
Inputs: no named parameters.
getSourceB
Get current audio input source
Inputs: no named parameters.
getStatusB
Get comprehensive device status
Inputs: no named parameters.
getStreamTypeB
Get the current streaming service (Spotify, AirPlay, Roon, etc.)
Inputs: no named parameters.
getTrebleB
Get current treble gain level
Inputs: no named parameters.
getTrebleFrequencyB
Get current treble frequency
Inputs: no named parameters.
getVoicingB
Get current voicing preset
Inputs: no named parameters.
getVolumeB
Get current music/audio volume level
Inputs: no named parameters.
listDevicesB
List all discovered Lyngdorf devices
Inputs: no named parameters.
listRoomPerfectPositionsB
List all RoomPerfect positions with their names from the device
Inputs: no named parameters.
listSourcesB
List all available input sources with their actual names from the device
Inputs: no named parameters.
listVoicingsB
List available voicing presets and show current selection
Inputs: no named parameters.
muteB
Mute the audio/music
Inputs: no named parameters.
nextA
Skip to next track. Works with streaming sources.
Inputs: no named parameters.
nextVoicingB
Switch to next voicing preset
Inputs: no named parameters.
pauseB
Pause music playback (same as play - it toggles). Works with streaming sources.
Inputs: no named parameters.
playA
Toggle music playback (play/pause). Works with streaming sources like Spotify, AirPlay, Roon, etc.
Inputs: no named parameters.
powerOffB
Turn the audio amplifier off
Inputs: no named parameters.
powerOnB
Turn the audio amplifier on
Inputs: no named parameters.
previousA
Go to previous track. Works with streaming sources.
Inputs: no named parameters.
previousVoicingB
Switch to previous voicing preset
Inputs: no named parameters.
selectDeviceC
Select and connect to a specific device by number
Inputs: device_number (required).
setBalanceC
Set left/right balance (L10-L1, 0, R1-R10)
Inputs: balance (required).
setBassB
Set bass gain level (-12 to +12 dB)
Inputs: gain (required).
setBassFrequencyC
Set bass frequency (20 to 800 Hz)
Inputs: frequency (required).
setRoomPerfectFocusC
Set RoomPerfect focus position (1-8)
Inputs: position (required).
setRoomPerfectGlobalB
Set RoomPerfect to Global position
Inputs: no named parameters.
setSourceC
Set input source
Inputs: source (required).
setTrebleC
Set treble gain level (-12 to +12 dB)
Inputs: gain (required).
setTrebleFrequencyB
Set treble frequency (1500 to 16000 Hz)
Inputs: frequency (required).
setVoicingC
Set voicing preset
Inputs: voicing (required).
setVolumeA
Set absolute volume level in dB. VOLUME GUIDANCE: dB scale is logarithmic - every 10dB increase doubles perceived loudness. Reference levels: -50 to -40dB (very quiet/background), -40 to -30dB (quiet conversation), -30 to -20dB (normal listening), -20 to -10dB (loud), -10 to 0dB (very loud), above 0dB (extremely loud, risk of speaker/hearing damage). Most music listening happens between -35 and -20 dB. Always be conservative when increasing volume.
Inputs: level (required).
togglePowerB
Toggle amplifier power state
Inputs: no named parameters.
unmuteB
Unmute the audio/music
Inputs: no named parameters.
volumeDownA
Decrease volume by 0.5dB steps. VOLUME GUIDANCE: Due to logarithmic nature of dB, single steps (0.5dB) are barely audible. For noticeable changes: use 4-6 steps (2-3dB) for moderate adjustments. Typical listening: -40 to -30dB (quiet background), -25 to -15dB (moderate), -10 to 0dB (loud). Always check current level first.
Inputs: steps.
volumeUpA
Increase volume by 0.5dB steps. VOLUME GUIDANCE: Due to logarithmic nature of dB, single steps (0.5dB) are barely audible. For noticeable changes: use 4-6 steps (2-3dB) for moderate adjustments, or 10+ steps for significant changes. Typical listening: -40 to -30dB (quiet background), -25 to -15dB (moderate), -10 to 0dB (loud). Always check current level first.
Inputs: steps.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 43 tools
Most tools have distinct purposes, but some pairs like 'play' and 'pause' (both toggle playback) or 'powerOn'/'powerOff'/'togglePower' could cause confusion due to overlapping functionality. The majority, however, target specific resources and actions clearly.
Tool names follow a consistent verb_noun pattern throughout, with clear prefixes like 'get', 'set', 'list', and action verbs. All use camelCase uniformly, making them predictable and easy to parse.
With 43 tools, the set feels excessive for controlling audio devices. Many tools could be consolidated (e.g., separate get/set for each audio parameter) without losing functionality, leading to a bloated interface that may overwhelm agents.
The tool set comprehensively covers the domain of Lyngdorf audio device control, including discovery, status retrieval, configuration (balance, bass, treble, etc.), playback management, and power operations. No obvious gaps exist for typical use cases.
Maintenance
Related MCP Connectors
Control a Loxone Miniserver smart home: lights, blinds, climate, scenes and energy.
Sonos MCP server: control your Sonos speakers from any MCP client. Play songs, artists and playlists, set volume, group rooms, move music to another room, switch to TV, spoken announcements and reminders. 27 tools, English and Chinese. Works through the official Sonos cloud, so there is no home bridge to install; sign in with OAuth. Requires the free ZoneFoundry iOS app.
MCP server for Yoto: manage cards, tracks, icons and family devices from any MCP client.
Control your existing Philips lights, Sonos speakers, Roborock vacuums and other supported devices through Port OS cloud. Give ChatGPT, Claude and other MCP-compatible assistants access to the devices you connect. Turn off the living room lights, play music on your speakers, adjust the thermostat, run a vacuum in a room, check a camera snapshot or find a connected tracker. Available actions depend on your linked provider accounts and each device’s supported capabilities. Port OS runs in the cloud; no local server is required. You choose the account, device and capability permissions each assistant receives. Device operations require user OAuth; public tool discovery does not grant device access. Port OS is in alpha. Setup: https://portoperatingsystem.com/docs/getting-started/ Support: https://portoperatingsystem.com/contact/
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceMCP server that wraps the Multiroom Audio Hub v2 REST API, providing 24 tools to control multiroom audio systems. Enables AI assistants to manage inputs, outputs, groups, routes, playback, and master mute.AGPL 3.0- AlicenseNot gradedqualityCmaintenanceEnables an AI agent to inspect and control Lyrion Music Server (Logitech Media Server) players via the LMS JSON-RPC API, including playback, volume, playlists, favorites, radio, and library search/browse.1MIT
- AlicenseAqualityCmaintenanceEnables full control of an Apple TV over the local network, including playback, remote navigation, app launching, deep links, and power management.13MIT
- AlicenseAqualityCmaintenanceEnables controlling Bluesound/BluOS players with transport, volume, multi-room grouping, presets, and search/play across streaming services like TIDAL and TuneIn.19MIT