karan_ksrk_ksrk_mcp_server_client
by karan-ksrkClaude Desktop Integration for KSRK MCP Server
Overview
The Claude Desktop Integration for KSRK MCP Server is a project designed to provide the latest information about a specific user (currently "ksrk") by integrating with the Claude Desktop application. This MCP server allows users to either add it to Claude Desktop or create a custom client to interact with it. The repository includes the necessary tools and configurations to set up and use the server effectively.
Tools
The project leverages several tools and libraries to achieve its functionality:
- OpenAI GPT-4: Used for processing user queries and generating responses.
- ScrapingDog API: Enables web scraping to fetch relevant information.
- BeautifulSoup: Parses HTML and XML documents for data extraction.
- httpx: Acts as the HTTP client for making web requests.
Configuration
Requirements
- Python 3.13
- Dependencies listed in
pyproject.toml
Installation
- Clone the repository:
shell git clone <repository-url> cd documentation - Create a virtual environment and activate it:
shell python -m venv .venv source .venv/bin/activate # On Windows use `.venv\Scripts\activate` - Install the dependencies:
shell pip install -r requirements.txt - Set up environment variables:
Create a.envfile in the root directory with the following content:
dotenv SCRAPING_DOG_API_KEY=your_scraping_dog_api_key OPENAI_API_KEY=your_openai_api_key
Usage
Running the Client
- Navigate to the root directory:
shell cd .. - Run the client:
shell python client.py - Enter your prompts in the interactive prompt loop. Type
quitorexitto stop the client.
Project Files
client.py
This file contains the main client code that interacts with the MCP server and OpenAI's GPT-4 model. It includes the following key components:
- MCPClient: Manages the connection to the MCP server and provides methods to retrieve available tools and call them.
- agent_loop: An asynchronous function that processes user queries 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 MCP server implementation. It includes the following key components:
- search_web: An asynchronous function that searches the web using the ScrapingDog API.
- fetch_url: An asynchronous function that fetches the content of a URL.
- about_ksrk: An MCP tool that searches for details about "ksrk" on a given website.
ksrk-mcp/test-website.py
This file contains a script to test website scraping using httpx and BeautifulSoup.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Acknowledgements
- OpenAI for providing the GPT-4 model.
- ScrapingDog for the web scraping API.
- BeautifulSoup for parsing HTML and XML documents.
- httpx for the HTTP client.
About
This MCP server is designed to fetch the latest information about a specific user (currently "ksrk"). Users can integrate this server with Claude Desktop or create a custom client to interact with it.
Invite Gmail Contacts
