Metadata-Version: 2.4
Name: labs-mcp-server
Version: 0.1.1
Summary: MCP Server with AI-powered tools including ElevenLabs text-to-speech. Ready for MCP Registry publication.
License: MIT
License-File: LICENSE
Keywords: mcp,model-context-protocol,elevenlabs,text-to-speech,ai-tools
Author: Luis Alberto Bolaños Salazar
Author-email: 68343185+albertbolanoss@users.noreply.github.com
Requires-Python: >=3.11,<4.0
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Dist: elevenlabs (>=2.0.0)
Requires-Dist: mcp (>=1.0.0)
Requires-Dist: pydantic (>=2.0.0)
Requires-Dist: pydantic-settings (>=2.0.0)
Requires-Dist: python-dotenv (>=1.0.0)
Project-URL: Documentation, https://github.com/albertbolanoss/labs-mcp-server#readme
Project-URL: Homepage, https://github.com/albertbolanoss/labs-mcp-server
Project-URL: Repository, https://github.com/albertbolanoss/labs-mcp-server
Description-Content-Type: text/markdown

# Labs MCP Server

<!-- mcp-name: io.github.albertbolanoss/labs_mcp -->

MCP (Model Context Protocol) server providing AI-powered tools for Claude, Cursor, and other MCP-compatible clients.

## Available Tools

| Tool | Description |
|------|-------------|
| `elevenlabs_text_to_speak` | Converts text to realistic spoken audio using ElevenLabs API |

## Installation

```bash
pip install labs-mcp-server
```

## Quick Start

### 1. Set Environment Variables

```bash
export ELEVENLABS_API_KEY="your-api-key"
```

### 2. Run the Server

```bash
# STDIO transport (for Claude Code, Cursor, etc.)
labs-mcp-server

# SSE transport (for web clients)
labs-mcp-server --transport sse --port 8000
```

### 3. Configure Your MCP Client

#### Claude Code (`~/.claude/settings.json`)

```json
{
  "mcpServers": {
    "labs-mcp": {
      "command": "labs-mcp-server",
      "args": []
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "labs-mcp": {
      "command": "labs-mcp-server",
      "args": []
    }
  }
}
```

## Environment Variables

| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `ELEVENLABS_API_KEY` | Yes | - | ElevenLabs API key |
| `ELEVENLABS_VOICE_ID` | No | `JBFqnCBsd6RMkjVDRZzb` | Default voice ID |
| `ELEVENLABS_MODEL_ID` | No | `eleven_multilingual_v2` | TTS model |
| `ELEVENLABS_OUTPUT_DIR` | No | `output` | Audio output directory |
| `MCP_SERVER_NAME` | No | `LabsMCPServer` | Server name |
| `LOG_LEVEL` | No | `INFO` | Logging level |

## Development

```bash
# Clone repository
git clone https://github.com/albertbolanoss/labs-mcp-server.git
cd labs-mcp-server

# Instalar
poetry install --with dev,sse

# Crear .env con API key
echo "ELEVENLABS_API_KEY=tu-key" > .env

# STDIO
poetry run labs-mcp-server

# Debug STDIO
npx @modelcontextprotocol/inspector poetry run labs-mcp-server


# SSE
poetry run labs-mcp-server --transport sse --port 8000

# Debud SSE
npx @modelcontextprotocol/inspector 
```

## License

MIT License - see [LICENSE](LICENSE) for details.

