Basic Mcp
What is Basic Mcp
basic-mcp is a voice assistant application built using the LiveKit Agents framework, designed to utilize Multimodal Control Protocol (MCP) tools for interaction with external services.
Use cases
Use cases for basic-mcp include creating interactive voice assistants for customer support, developing educational applications that respond to voice commands, and implementing automated systems for voice-driven tasks in smart homes or businesses.
How to use
To use basic-mcp, clone the repository, install the required packages, set up a .env file with your API keys and MCP server URL, and run the agent using the LiveKit CLI with the command ‘python agent.py console’.
Key features
Key features include voice-based interaction with an AI assistant, integration with MCP tools, speech-to-text capabilities using Deepgram, natural language processing with OpenAI’s GPT-4o, text-to-speech functionality, and voice activity detection using Silero.
Where to use
basic-mcp can be used in various fields such as customer service, virtual assistants, educational tools, and any application that benefits from voice interaction and automation.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Basic Mcp
basic-mcp is a voice assistant application built using the LiveKit Agents framework, designed to utilize Multimodal Control Protocol (MCP) tools for interaction with external services.
Use cases
Use cases for basic-mcp include creating interactive voice assistants for customer support, developing educational applications that respond to voice commands, and implementing automated systems for voice-driven tasks in smart homes or businesses.
How to use
To use basic-mcp, clone the repository, install the required packages, set up a .env file with your API keys and MCP server URL, and run the agent using the LiveKit CLI with the command ‘python agent.py console’.
Key features
Key features include voice-based interaction with an AI assistant, integration with MCP tools, speech-to-text capabilities using Deepgram, natural language processing with OpenAI’s GPT-4o, text-to-speech functionality, and voice activity detection using Silero.
Where to use
basic-mcp can be used in various fields such as customer service, virtual assistants, educational tools, and any application that benefits from voice interaction and automation.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
LiveKit Agent with MCP Tools
A voice assistant application built using the LiveKit Agents framework, capable of using Multimodal Control Protocol (MCP) tools to interact with external services.
Features
- Voice-based interaction with a helpful AI assistant
- Integration with MCP tools from external servers
- Speech-to-text using Deepgram
- Natural language processing using OpenAI’s GPT-4o
- Text-to-speech using OpenAI
- Voice activity detection using Silero
Prerequisites
- Python 3.9+
- API keys for OpenAI and Deepgram
- MCP server endpoint
Installation
-
Clone this repository:
git clone https://github.com/livekit-examples/basic-mcp.git cd basic-mcp -
Install the required packages:
pip install -r requirements.txt -
Create a
.envfile with your API keys and configuration:OPENAI_API_KEY=your_openai_api_key DEEPGRAM_API_KEY=your_deepgram_api_key ZAPIER_MCP_URL=your_mcp_server_url
Usage
Run the agent with the LiveKit CLI:
python agent.py console
The agent will connect to the specified LiveKit room and start listening for voice commands.
Project Structure
agent.py: Main agent implementation and entrypointmcp_client/: Package for MCP server integrationserver.py: MCP server connection handlersagent_tools.py: Integration of MCP tools with LiveKit agentsutil.py: Utility functions for MCP client
Acknowledgements
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
