Gemini Live Mcp
What is Gemini Live Mcp
Gemini Live MCP is an MCP client that leverages the Gemini Live API to facilitate voice-based interactions with Gemini. It also supports the addition of multiple MCP servers for enhanced functionality.
Use cases
Use cases for Gemini Live MCP include developing voice-controlled applications, creating interactive systems for customer service, and integrating voice commands into existing software solutions.
How to use
To use Gemini Live MCP, clone the repository, set up your environment variables by adding your Google API key to a .env file, and create an MCP configuration file to define your MCP servers. Finally, run the application using the command ‘uv run main.py --mode=none’, selecting the desired mode.
Key features
Key features include voice-based interaction with Gemini through the Gemini Live API and support for multiple MCP servers, allowing for extended capabilities.
Where to use
Gemini Live MCP can be used in various fields such as voice recognition applications, interactive voice response systems, and any domain requiring voice-based communication with software.
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 Gemini Live Mcp
Gemini Live MCP is an MCP client that leverages the Gemini Live API to facilitate voice-based interactions with Gemini. It also supports the addition of multiple MCP servers for enhanced functionality.
Use cases
Use cases for Gemini Live MCP include developing voice-controlled applications, creating interactive systems for customer service, and integrating voice commands into existing software solutions.
How to use
To use Gemini Live MCP, clone the repository, set up your environment variables by adding your Google API key to a .env file, and create an MCP configuration file to define your MCP servers. Finally, run the application using the command ‘uv run main.py --mode=none’, selecting the desired mode.
Key features
Key features include voice-based interaction with Gemini through the Gemini Live API and support for multiple MCP servers, allowing for extended capabilities.
Where to use
Gemini Live MCP can be used in various fields such as voice recognition applications, interactive voice response systems, and any domain requiring voice-based communication with software.
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
Gemini Live MCP
Gemini Live MCP is an MCP client that utilizes the Gemini Live API to enable voice-based interaction with Gemini. Additionally, it now supports adding MCP servers for extended functionality.
Features
- Voice-based interaction with Gemini via the Gemini Live API
- Support for multiple MCP servers
Installation
-
Clone the repository:
git clone https://github.com/allenbijo/gemini-live-mcp.git cd gemini-live-mcp -
Set up environment variables:
Create a.envfile in the project root and add your Google API key:GOOGLE_API_KEY=your_google_api_key_here -
Create MCP configuration file:
Define your MCP servers by creating amcp_config.jsonfile in the project root.
Example structure:{ "mcpServers": { "sysinfo": { "command": "uv", "args": [ "--directory", "D:\\WorksOfGreatness\\mcp-sysinfo", "run", "sysinfo.py" ] } } }
Usage
Run the application using the following command:
uv run main.py --mode=none
# mode can be none, camera, screen
Modes
none: Runs without any visual interface.screen: Displays results on the screen.camera: Uses the camera for interaction.
License
This project is licensed under the MIT License.
Contributing
Feel free to submit issues or pull requests to improve the project.
Contact
For questions or support, reach out via GitHub Issues.
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.
