The Sonos MCP Server allows you to control and interact with Sonos devices on your network:
Discover Devices: Find Sonos devices on your network
Control Playback: Play, pause, stop, skip tracks (next/previous)
Manage Queues: Retrieve queue information, modify queues, play specific tracks by index, remove tracks
Retrieve Information: Get device states, current track details (artist, title, album, duration), and speaker information
Control Volume: Get or set device volume levels
Manage Play Modes: Set or retrieve play modes (shuffle, repeat, normal)
Enable Party Mode: Synchronize multiple Sonos speakers
Provides tools for controlling Sonos audio devices, including discovering devices on a network, controlling playback (play, pause, stop, next, previous), managing playback queues, adjusting volume, retrieving now playing information, and enabling party mode across speakers.
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., "@Sonos MCP Server pause the living room speaker"
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.
This project is a Sonos MCP (Model Context Protocol) server that allows you to control and interact with Sonos devices on your network. It provides various functionalities such as discovering devices, controlling playback, retrieving device states, and managing queues.
Discover Sonos devices on the network
Retrieve and control playback state for devices
Manage playback queues
Expose functionalities as MCP tools
Related MCP server: YARR Media Stack MCP Server
Python 3.12+
uv for managing Python projects
pip install git+https://github.com/WinstonFassett/sonos-mcp-server.gitClone the repository:
git clone https://github.com/WinstonFassett/sonos-mcp-server.git
cd sonos-mcp-serverInstall the required dependencies using uv:
uv syncRun the server using stdio:
uv run mcp run server.pyThe server supports the MCP streamable-http transport natively (mcp SDK >= 1.12). No proxy needed:
SONOS_MCP_TRANSPORT=streamable-http \
SONOS_MCP_HOST=127.0.0.1 \
SONOS_MCP_PORT=8090 \
uv run sonos-mcp-serverEndpoint: http://127.0.0.1:8090/mcp
Environment variables:
Var | Default | Notes |
|
|
|
|
| HTTP bind address |
|
| HTTP port (path is |
| (localhost only) | Extra Host headers to accept, comma-separated. Needed when serving behind a proxy with a different hostname (e.g. |
| (SSDP discovery) | Comma-separated speaker IPs. Skips SSDP multicast and resolves names over unicast SOAP — required when the process can't multicast (e.g. launchd without Local Network permission). |
Older alternative (deprecated — prefer streamable-http above):
npx -y supergateway --port 8000 --stdio "uv run mcp run server.py"To run the server in "development" mode with the MCP Inspector:
uv run mcp dev server.pyThis command hosts an MCP Inspector for testing and debugging purposes.
To run the server with SSE in development mode, use the SSE command for supergateway, and in a second terminal window run:
npx @modelcontextprotocol/inspectorAfter publishing to git, users can install directly:
mcp install git+https://github.com/WinstonFassett/sonos-mcp-server.gitOr add to Claude Desktop config:
{
"mcpServers": {
"sonos": {
"command": "sonos-mcp-server"
}
}
}Use the exposed MCP tools to interact with Sonos devices. The available tools include:
get_all_device_states: Retrieve the state information for all discovered Sonos devices.
now_playing: Retrieve information about currently playing tracks on all Sonos devices.
get_device_state: Retrieve the state information for a specific Sonos device.
pause, stop, play: Control playback on a Sonos device.
next, previous: Skip tracks on a Sonos device.
get_queue, get_queue_length: Manage the playback queue for a Sonos device.
mode: Get or set the play mode of a Sonos device.
partymode: Enable party mode on the current Sonos device.
speaker_info: Retrieve speaker information for a Sonos device.
get_current_track_info: Retrieve current track information for a Sonos device.
volume: Get or set the volume of a Sonos device.
skip, play_index, remove_index_from_queue: Manage tracks in the queue for a Sonos device.
add_service_tracks_to_queue: Add tracks from music services like Spotify, Apple Music, Tidal, or Deezer to the Sonos queue.
After making changes:
git add .
git commit -m "Description of changes"
git pushUsers can update with:
pip install --upgrade git+https://github.com/WinstonFassett/sonos-mcp-server.gitThis project is licensed under the MIT License. See the LICENSE file for details.
Retrieve the state information for all discovered Sonos devices.
Returns: List[Dict[str, Any]]: A list of dictionaries containing state information for each device.
Inputs: no named parameters.
Retrieve current track information for a Sonos device.
Args: name: The name of the device to retrieve track information from. If None, uses the current device.
Returns: Dict[str, str]: A dictionary containing the current track's artist, title, album, playlist position, and duration.
Inputs: name.
Retrieve the state information for a specific Sonos device.
Args: name: The name of the device to retrieve state information for. If None, uses the current device.
Returns: Dict[str, Any]: A dictionary containing the device's name, volume, state, and current track information.
Inputs: name.
Retrieve the queue of tracks for a Sonos device.
Args: name: The name of the device to retrieve the queue from. If None, uses the current device.
Returns: List[Dict[str, Any]]: A list of dictionaries containing track information in the queue.
Inputs: name.
Retrieve the queue length for a Sonos device.
Args: name: The name of the device to retrieve the queue length from. If None, uses the current device.
Returns: int: The length of the queue.
Inputs: name.
Get or set the play mode of a Sonos device.
Args: mode: The play mode to set (e.g., "NORMAL", "SHUFFLE_NOREPEAT", "SHUFFLE", "REPEAT_ALL"). If None, returns the current mode. name: The name of the device to set the mode for. If None, uses the current device.
Returns: str: The current play mode after the operation.
Inputs: mode, name.
Skip to the next track on a Sonos device.
Args: name: The name of the device to skip the track on. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after skipping to the next track, including name, volume, state, and track info.
Inputs: name.
Retrieve information about currently playing tracks on all Sonos devices.
Returns: List[Dict[str, str]]: A list of dictionaries containing the name, title, artist, and album of currently playing tracks.
Inputs: no named parameters.
Enable party mode on the current Sonos device.
Returns: Dict[str, Any]: The device's state after enabling party mode, including name, volume, state, and track info.
Inputs: no named parameters.
Pause playback on a Sonos device.
Args: name: The name of the device to pause. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after pausing, including name, volume, state, and track info.
Inputs: name.
Start playback on a Sonos device.
Args: name: The name of the device to start playback on. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after starting playback, including name, volume, state, and track info.
Inputs: name.
Play a specific track from the queue on a Sonos device.
Args: index: The index of the track to play. name: The name of the device to play the track on. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after playing the specified track, including name, volume, state, and track info.
Raises: ValueError: If the index is out of the queue's range.
Inputs: index (required), name.
Skip to the previous track on a Sonos device.
Args: name: The name of the device to skip the track on. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after skipping to the previous track, including name, volume, state, and track info.
Inputs: name.
Remove a specific track from the queue on a Sonos device.
Args: index: The index of the track to remove. name: The name of the device to remove the track from. If None, uses the current device.
Returns: List[Dict[str, Any]]: The updated queue after removing the track.
Raises: ValueError: If the index is out of the queue's range.
Inputs: index (required), name.
Skip tracks in the queue for a Sonos device.
Args: increment: The number of tracks to skip forward. Defaults to 1. name: The name of the device to skip tracks on. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after skipping tracks, including name, volume, state, and track info.
Raises: ValueError: If the new track position is out of the queue's range.
Inputs: increment, name.
Retrieve speaker information for a Sonos device.
Args: name: The name of the device to retrieve speaker information from. If None, uses the current device.
Returns: Dict[str, str]: A dictionary containing speaker information.
Inputs: name.
Stop playback on a Sonos device.
Args: name: The name of the device to stop. If None, uses the current device.
Returns: Dict[str, Any]: The device's state after stopping, including name, volume, state, and track info.
Inputs: name.
Get or set the volume of a Sonos device.
Args: volume: The volume level to set (0-99). If None, returns current volume. name: The name of the device to control. If None, uses the current device.
Returns: int: The current volume level after the operation.
Raises: ValueError: If volume is not between 0 and 99. ValueError: If the specified device is not found.
Inputs: name, volume.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 18 tools
Most tools have distinct purposes, but some overlap exists. For example, 'skip' and 'next' both advance tracks, though 'skip' offers more flexibility with an increment parameter. 'get_current_track_info' and 'now_playing' both retrieve track info, but 'now_playing' covers all devices while 'get_current_track_info' is per-device. Descriptions help clarify these differences, but minor confusion could occur.
Tool names follow a consistent snake_case pattern throughout, with clear verb_noun structures like 'get_device_state', 'play_index', and 'remove_index_from_queue'. However, there are minor deviations: 'mode' and 'volume' are single-word nouns without verbs, and 'partymode' is a compound word instead of snake_case, slightly breaking the pattern.
With 18 tools, the count is slightly high but reasonable for a Sonos control server, covering device states, playback control, queue management, and settings. It might feel a bit heavy, but each tool serves a specific function without obvious redundancy, making it well-scoped for the domain.
The tool set provides comprehensive coverage for Sonos device management. It includes CRUD-like operations for queue management (get, remove), full playback control (play, pause, stop, next, previous, skip), device state retrieval, volume and mode settings, and specialized functions like party mode. No significant gaps are apparent for core audio control workflows.
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.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server for Yoto: manage cards, tracks, icons and family devices from any MCP client.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
