Audio MCP Server

An MCP (Model Context Protocol) server that provides audio input/output capabilities for AI assistants like Claude. This server enables Claude to

Local serverstdioPython

What is the Audio MCP server?

If you want an AI assistant working directly with Audio, the audio mcp server is the bridge. An MCP (Model Context Protocol) server that provides audio input/output capabilities for AI assistants like Claude. This server enables Claude to interact with your computer's audio system, including recording from microphones and playing audio through speakers.

What Audio does

An MCP (Model Context Protocol) server that provides audio input/output capabilities for AI assistants like Claude. This server enables Claude to interact with your computer's audio system, including recording from microphones and playing audio through speakers.

Key capabilities

  • List Audio Devices — View all available microphones and speakers on your system
  • Record Audio — Capture audio from any microphone with customizable duration and quality
  • Playback Recordings — Play back your most recent recording
  • Audio File Playback — Play audio files through your speakers
  • Text-to-Speech — (Placeholder for future implementation)

Tools it exposes

Once connected, the assistant can call these 5 tools directly:

  • list_audio_devices — Lists all available audio input and output devices on your system
  • record_audio — Parameters: - duration: Recording duration in seconds (default: 5) - sample_rate: Sample rate in Hz (default: 44100) - channels: Number of audio channels
  • play_latest_recording — The play_latest_recording tool exposed by this server
  • play_audio — Parameters: - text: The text to convert to speech - voice: The voice to use (default: "default")
  • play_audio_file — Parameters: - file_path: Path to the audio file - device_index: Specific output device index to use (default: system default)

Installing the audio mcp server

The server is distributed via npm as @smithery/cli, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

The server reads one environment variable: PYTHONPATH. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  • Python 3.8 or higher - Audio input/output devices on your system

Where it fits

AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. Audio sits in that group, and the shape of its toolset — list_audio_devices, record_audio, play_latest_recording among others — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • Maintained by GongRzhe, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the audio mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
list_audio_devicesLists all available audio input and output devices on your system.
record_audioParameters: - duration: Recording duration in seconds (default: 5) - sample_rate: Sample rate in Hz (default: 44100) - channels: Number of audio channels (default: 1) - device_index: Specific input device index to use (d
play_latest_recordingThe play_latest_recording tool exposed by this server.
play_audioParameters: - text: The text to convert to speech - voice: The voice to use (default: "default")
play_audio_fileParameters: - file_path: Path to the audio file - device_index: Specific output device index to use (default: system default)

How to install the Audio MCP server

{
  "mcpServers": {
    "audio": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "PYTHONPATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.8 or higher - Audio input/output devices on your system
VariableDescriptionRequired
PYTHONPATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Audio to list audio devices.
  • Use Audio to record audio.
  • Use Audio to play latest recording.

Frequently asked questions

It connects Audio to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (list_audio_devices, record_audio, play_latest_recording, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Audio directly.