labs-mcp-server 0.1.0

MCP Server with AI-powered tools including ElevenLabs text-to-speech. Ready for MCP Registry publication.

Labs MCP Server

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

pip install labs-mcp-server

Quick Start

1. Set Environment Variables

export ELEVENLABS_API_KEY="your-api-key"

2. Run the Server

# 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)

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

Claude Desktop (claude_desktop_config.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

# 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 for details.