Ksrk Mcp Server Client
About
MCP server to get latest information about me (for now), you can add that mcp server to claude desktop or create custom client which you can see in the file
Details
- Author
- karan-ksrk
- Downloads
- 315
- Categories
- Other
Jump to
- MCPClient class for server connection and tool calls
- agent_loop processes user queries using GPT‑4
- search_web searches the web via ScrapingDog API
- fetch_url retrieves content from a given URL
- about_ksrk searches for “ksrk” on specified websites
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ksrk Mcp Server ClientCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, create and activate a virtual environment, install dependencies from requirements.txt, and set environment variables SCRAPING_DOG_API_KEY and OPENAI_API_KEY. Run python client.py from the root directory, then enter prompts; type quit or exit to stop.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ksrk mcp server client": {
"ksrk-mcp-server-client": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"ksrk-mcp-server-client": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}Requirements
- Python 3.13
- Dependencies listed in pyproject.toml
Installation
1. Clone the repository:
git clone <repository-url>
cd documentation
2. Create a virtual environment and activate it:
python -m venv .venv
source .venv/bin/activate # On Windows use .venv\Scripts\activate
3. Install the dependencies:
pip install -r requirements.txt
4. Set up environment variables:
Create a .env file in the root directory with the following content:
SCRAPING_DOG_API_KEY=your_scraping_dog_api_key
OPENAI_API_KEY=your_openai_api_key
Usage
Running the Client
1. Navigate to the root directory:
cd ..
2. Run the client:
python client.py
3. Enter your prompts in the interactive prompt loop. Type quit or exit to 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: A class that 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.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
