Ksrk MCP Server Client

🚀 Documentation Project

This project provides a client and server for interacting with MCP and using OpenAI's GPT - 4 model, along with necessary setup and usage instructions.

🚀 Quick Start

Requirements

• Python 3.13
• Dependencies listed in pyproject.toml

Installation

1. Clone the repository:

   git clone <repository-url>
   cd documentation
   

2. Create and activate a virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # Use `.venv\Scripts\activate` on Windows
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Set environment variables: Create a .env file in the project root directory with the following content:

   SCRAPING_DOG_API_KEY=your_scraping_dog_api_key
   OPENAI_API_KEY=your_openai_api_key
   

Usage Examples

Basic Usage

To run the client:

1. Navigate to the root directory:

   cd ..
   

2. Run the client:

   python client.py
   

3. Enter your questions in the interactive prompt. Type quit or exit to stop the client.

📚 Documentation

Project Files

client.py

This file contains the main client code for interacting with the MCP server and OpenAI's GPT - 4 model. It includes the following key components:

• MCPClient: A class that manages the connection to the MCP server and provides methods to call available tools.
• agent_loop: An asynchronous function that processes user queries and analyzes them using the LLM and available tools.
• main: The main function that sets up the MCP server, initializes tools, and runs the interactive loop.

ksrk - mcp/ksrk - mcp - server.py

This file contains the implementation of the MCP server. It includes the following key components:

• search_web: An asynchronous function that uses the ScrapingDog API for web searches.
• fetch_url: An asynchronous function for fetching the content of a specified URL.
• about_ksrk: An MCP tool for searching detailed information about "ksrk" on a specified website.

ksrk - mcp/test - website.py

This file contains a script for testing website scraping using httpx and BeautifulSoup.

📄 License

This project is released under the MIT License. For more details, see the LICENSE file.

👏 Acknowledgments

• OpenAI for providing the GPT - 4 model.
• ScrapingDog for the web scraping API.
• BeautifulSoup for parsing HTML and XML documents.
• [httpx](https://www.python - httpx.org) for the HTTP client.