# Noisy Studio MCP server

> Provides a voice interface for Claude Code, enabling speech recognition and spoken replies during agentic coding tasks.

- Repository: https://github.com/noisy/noisy-coding
- Page: https://hostedmcp.org/servers/noisy/noisy-coding
- Transport: remote
- Stars: 14
- License: MIT
- Latest version: 2.13.3

## Install

### Claude Code

```sh
claude mcp add --env 'XAI_API_KEY=<YOUR_XAI_API_KEY>' noisy-coding -- docker run -i --rm docker.io/noisy/noisy-coding:2.13.3
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "noisy-coding": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/noisy/noisy-coding:2.13.3"
      ],
      "env": {
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "noisy-coding": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/noisy/noisy-coding:2.13.3"
      ],
      "env": {
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"noisy-coding","type":"stdio","command":"docker","args":["run","-i","--rm","docker.io/noisy/noisy-coding:2.13.3"],"env":{"XAI_API_KEY":"<YOUR_XAI_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "noisy-coding": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/noisy/noisy-coding:2.13.3"
      ],
      "env": {
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add noisy-coding --env 'XAI_API_KEY=<YOUR_XAI_API_KEY>' -- docker run -i --rm docker.io/noisy/noisy-coding:2.13.3
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.noisy-coding]
command = "docker"
args = ["run", "-i", "--rm", "docker.io/noisy/noisy-coding:2.13.3"]

[mcp_servers.noisy-coding.env]
XAI_API_KEY = "<YOUR_XAI_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'XAI_API_KEY=<YOUR_XAI_API_KEY>' noisy-coding docker -- run -i --rm docker.io/noisy/noisy-coding:2.13.3
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "noisy-coding": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/noisy/noisy-coding:2.13.3"
      ],
      "env": {
        "XAI_API_KEY": "<YOUR_XAI_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `XAI_API_KEY` | no | yes | xAI API key for Grok voice synthesis and transcription (configured once on the dashboard, stored in the config volume) |

## FAQ

### How do I install Noisy Studio for Claude Code?

Download the macOS Apple Silicon app from the Releases page, move it to Applications, and then install the companion plugin via the Claude plugin marketplace.

### Does Noisy Studio require Python to be installed separately?

No, the app includes its own Python engine, so a standard Claude installation does not require Python or a separate service manager.

### Can I use Noisy Studio offline?

Yes, offline providers will download their models on the first use and then run locally.

### What platform is officially supported?

macOS is the validated release platform, while other platforms are currently for source development.