mcpField
K
Ksrk Mcp Server Client

Ksrk Mcp Server Client

Local
github.com/karan-ksrkOther2Updated 83w ago
Repository

About Ksrk Mcp Server Client

Ksrk Mcp Server Client combines an MCP server that searches the web for information about ksrk with an interactive Python client using GPT-4. It is intended for queries about ksrk and includes tools to search websites and fetch page content.

Key features

  1. 01Web search via ScrapingDog
  2. 02URL content retrieval
  3. 03Website-specific ksrk lookup
  4. 04Interactive GPT-4 query loop

Use cases

  1. 01Search the web for information about ksrk
  2. 02Retrieve and inspect content from a URL

MCP support

The MCP server exposes web search, URL fetching, and the about_ksrk tool. The included client connects to the server and calls its tools while processing queries with GPT-4.

#ksrk#mcp#server-client

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.