MCP Use Voice Assistant MCP Server

<h2 align="center">built with</h2> <picture> <source media="(prefers-color-scheme: dark)" srcset="static/logo_white.svg"> <source

Local serverstdioPython

What is the MCP Use Voice Assistant MCP server?

built with . The mcp use voice assistant mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 5 defined tools rather than through you.

What it actually does

  • 🎤 Voice Input: Real-time speech-to-text using OpenAI Whisper
  • 🔊 Voice Output: High-quality text-to-speech using ElevenLabs (with pyttsx3 fallback)
  • 🤖 AI-Powered: Conversational AI with memory persistence
  • 🌐 Multiple Model Providers: Works with any LLM provider that supports tool calling (OpenAI, Anthropic, Groq, LLama, etc.)
  • 🛠️ Multi-Tool Integration: Seamlessly connects to any MCP servers:
  • 💾 Conversational Memory: Maintains context across interactions

Its toolset

Everything the assistant can do here goes through one of these:

  • macOS — brew install portaudio
  • Windows — PyAudio wheel includes PortAudio
  • playwright — Web automation and browser control
  • linear — Task and project management
  • Prerequisites — 1. Python 3.11+ 2. uv (Python package manager): pip install uv or pipx install uv 3. Node.js (for MCP servers) 4. **System

Configuration

You will need 8 environment variables: YOUR_API_KEY, OPENAI_API_KEY, ELEVENLABS_API_KEY, ANTHROPIC_API_KEY, GROQ_API_KEY, ELEVENLABS_VOICE_ID, LINEAR_API_KEY, GITHUB_PERSONAL_ACCESS_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  1. Python 3.11+ 2. uv (Python package manager): pip install uv or pipx install uv 3. Node.js (for MCP servers) 4. System dependencies: - macOS: brew install portaudio - Ubuntu/Debian: sudo apt-get install portaudio19-dev - Windows: PyAudio wheel includes PortAudio

Adding it to your client

The server ships on npm as downloads, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Use Voice Assistant's toolset — macOS, Windows, playwright and 2 more — is a fair guide to whether it matches your workflow. It is maintained by mcp-use; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Use Voice Assistant's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp use voice assistant mcp server does with a few real requests.

Available tools

ToolWhat it does
macOSbrew install portaudio
WindowsPyAudio wheel includes PortAudio
playwrightWeb automation and browser control
linearTask and project management
Prerequisites1. **Python 3.11+** 2. **uv** (Python package manager): pip install uv or pipx install uv 3. **Node.js** (for MCP servers) 4. **System dependencies**: - macOS: brew install portaudio - Ubuntu/Debian: sudo apt-get install

How to install the MCP Use Voice Assistant MCP server

{
  "mcpServers": {
    "use-voice-assistant": {
      "command": "npx",
      "args": ["-y", "downloads"],
      "env": {
        "YOUR_API_KEY": "your-value",
        "OPENAI_API_KEY": "your-value",
        "ELEVENLABS_API_KEY": "your-value",
        "ANTHROPIC_API_KEY": "your-value",
        "GROQ_API_KEY": "your-value",
        "ELEVENLABS_VOICE_ID": "your-value",
        "LINEAR_API_KEY": "your-value",
        "GITHUB_PERSONAL_ACCESS_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  1. Python 3.11+ 2. uv (Python package manager): pip install uv or pipx install uv 3. Node.js (for MCP servers) 4. System dependencies: - macOS: brew install portaudio - Ubuntu/Debian: sudo apt-get install portaudio19-dev - Windows: PyAudio wheel includes PortAudio
VariableDescriptionRequired
YOUR_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
ELEVENLABS_API_KEYCredential the server authenticates with.Yes
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
GROQ_API_KEYCredential the server authenticates with.Yes
ELEVENLABS_VOICE_IDConfiguration value read at startup.Optional
LINEAR_API_KEYCredential the server authenticates with.Yes
GITHUB_PERSONAL_ACCESS_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use MCP Use Voice Assistant to macOS.
  • Use MCP Use Voice Assistant to Windows.
  • Use MCP Use Voice Assistant to playwright.

Frequently asked questions

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