MCP Event

🚀 AI Maker Space: MCP Events

This project demonstrates the functionality of an MCP (Model Context Protocol) server that uses the Tavily API to implement web search capabilities. The server is designed to run in standard input/output (stdio) transmission mode.

🚀 Quick Start

The MCP server processes web search queries by calling the Tavily API. It is built with the following key components:

• TavilyClient: A client for interacting with the Tavily API to perform web searches.

✨ Features

Prerequisites

• Python 3.13 or higher
• A valid Tavily API key

📦 Installation

1. Clone the repository:

   git clone <repository-url>
   cd <repository-directory>
   

2. Configure environment variables: Copy .env.sample to .env and add your Tavily API key:

   TAVILY_API_KEY=your_api_key_here
   

💻 Usage Examples

Run the MCP Server

To start the MCP server, you need to add the following content to the MCP profile in Cursor:

{
    "mcpServers":  {
        "websearch-server": {
            "command" : "uv",
            "args" : ["--directory", "/ПУТЬ/ДО/РЕПОЗИТОРИЮ", "run", "server.py"]
        }
    }
}

The server will start and listen for commands on standard input/output.

How to Use

The server provides a web_search tool that can be used to search for information about a given query. This is achieved by calling the web_search function and passing the required query string.

📄 License

This project is licensed under the MIT License. Please see the LICENSE file for more details.

🤝 Contribution

Contributions are welcome! For any changes, please open an issue or submit a pull request.