mcpField
M
MCP Play Sound Server

MCP Play Sound Server

Local
github.com/davidterenMedia & Design1Updated 73w ago
Repository

About MCP Play Sound Server

An early-stage MCP server for playing audio notifications for AI agents, currently tested only on macOS. It offers a bundled sound, custom audio playback, and tools for checking playback and device status.

Key features

  1. 01Play notification sounds
  2. 02Bundled default sound
  3. 03Custom WAV, MP3, FLAC, OGG, M4A
  4. 04Fallback to default sound
  5. 05Audio status and device tools

Use cases

  1. 01Signal completion of coding tasks
  2. 02Play a configured custom notification
  3. 03Check audio status and output devices

MCP support

Exposes tools to MCP clients for playing notification sounds, testing playback, checking audio status, and listing audio devices.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Play Sound Server

A Model Context Protocol (MCP) server that provides audio playback functionality for AI agents. This server enables AI agents to play sound notifications when coding tasks are completed.

⚠️ Early Version / Proof of Concept This is an early implementation currently tested only on macOS. Future versions will support additional platforms.

Features

  • Audio Notifications: Play sound alerts when AI tasks complete
  • Default Sound: Bundled notification sound for immediate use
  • Custom Audio: Support for custom audio files (WAV, MP3, FLAC, OGG, M4A)
  • Intelligent Fallback: Automatic fallback to default sound if custom audio fails
  • macOS Support: Currently tested on macOS using AFPlay and SimpleAudio

Installation & Setup

Development Setup
  1. Clone and install:
git clone <repository-url>
cd play-sound-mcp-server
python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -e ".[dev]"
  1. Configure Claude Desktop: Add to your claude_desktop_config.json:
{
  "mcpServers": {
    "play-sound": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/play-sound-mcp-server",
        "run",
        "mcp-server-play-sound"
      ]
    }
  }
}
  1. Test: Restart Claude Desktop and ask: "Can you play a notification sound?"

Configuration

Environment variables (optional):

  • CUSTOM_SOUND_PATH: Path to custom audio file
  • VOLUME_LEVEL: Playback volume (0.0-1.0, default: 0.8)
  • ENABLE_FALLBACK: Enable fallback to default sound (default: true)
  • AUDIO_DEVICE: Specific audio output device name (e.g., "Mac Studio Speakers")

Available Tools

play_notification_sound

Plays a notification sound to alert the user.

Parameters:

  • custom_sound_path (optional): Path to custom audio file
  • message (optional): Context message for the notification
get_audio_status

Returns current audio system status and configuration.

test_audio_playback

Tests audio playback functionality.

Parameters:

  • use_custom (optional): Test with custom sound if configured
list_audio_devices

Lists all available audio output devices on the system.

Returns:

  • List of available audio devices with their properties
  • Current configured device (if any)
  • Default device information

Development

Prerequisites
  • Python 3.10+
  • uv (recommended) or pip
Testing
pytest tests/

License

MIT License - see the LICENSE file for details.

Acknowledgments

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.