Play Sound

Model Context Protocol server that provides audio playback functionality for AI agents. Play notification sounds when coding tasks complete. Early version/proof of concept - macOS only.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "davidteren-play-sound-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/play-sound-mcp-server",
        "run",
        "mcp-server-play-sound"
      ],
      "env": {
        "AUDIO_DEVICE": "Mac Studio Speakers",
        "VOLUME_LEVEL": "0.8",
        "ENABLE_FALLBACK": "true",
        "CUSTOM_SOUND_PATH": "YOUR_PATH_TO_CUSTOM_SOUND"
      }
    }
  }
}

You are outfitting a lightweight MCP server that plays audio notifications for AI tasks. This server is designed to quickly alert you with sound when an AI-assisted task completes, with a bundled default tone and optional custom audio support. It is currently validated on macOS and can fall back to the default sound if a custom file can’t be played.

How to use

To use the Play Sound MCP server, run it as a local, stdio-based MCP endpoint and connect your MCP client to trigger audio playback. You can start by configuring your client to call the available endpoints that play a notification sound, test audio playback, or query the current audio setup. When a task completes, your client will request a notification sound, which will be played through your designated output device.

You can perform common interactions such as:

How to install

Prerequisites: Python 3.10+ and a Python environment tool (venv) are recommended.

Install and set up the development environment with these steps:

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]"

Configuration and runtime start

You configure the MCP client (Claude Desktop in this setup) to start the server through an MCP command. The following example shows how to wire the local MCP server using an inline command. This config assumes you will run the server from a local directory.

{
  "mcpServers": {
    "play_sound": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/your/play-sound-mcp-server",
        "run",
        "mcp-server-play-sound"
      ]
    }
  }
}

Run and test commands

After wiring the MCP server in your client, you can test playback by triggering a notification sound. Use your client’s interface to request a notification sound, or run a quick test command provided by your setup to confirm audio playback works as expected.

Available tools

play_notification_sound

Plays a notification sound to alert the user. Optional parameter allows a custom_sound_path and a context message.

get_audio_status

Returns current audio system status and configuration.

test_audio_playback

Tests audio playback functionality. Optional parameter use_custom tests with a configured custom sound.

list_audio_devices

Lists all available audio output devices and reports the current device and default information.

Built by

VeilStrat

AI signals for GTM teams