Kopilot-MCP-test

Kopilot-MCP-test

0
os_automation

Kopilot MCP is a project that creates an AI Kubernetes agent using the Model Context Protocol (MCP) to interact with Kubernetes resources through natural language commands. It allows customization of large language models to perform operations resembling kubectl commands and facilitates standardized tool integration using MCP.

Kopilot MCP

A MCP remake of a previous project.

Key Features

  • Create an AI Kubernetes agent using MCP.
  • Interact with Kubernetes resources using natural language.
  • Customize LLM provider to perform "kubectl-like" commands.
  • Learn how to use MCP to standardize tool calling.

Tech Stack

  • Dynaconf
  • Kubernetes
  • LangChain
  • Loguru
  • OpenAI

Getting Started

Prerequisites

  • Python 3.12+
  • uv
  • API key from LLM provider
  • Kubernetes cluster

Setup

  1. Clone this repository.
  2. Configure and rename example.toml.
  3. Install dependencies.

Run

  1. Run the MCP client.
  2. Interact using natural language.

Project Structure

  • kopilot-mcp/
  • README.md
  • config/
  • mcp_client.py
  • mcp_server.py
  • mcp_server_factory.py
  • pyproject.toml
  • scheme/
  • utils/
  • uv.lock

Contributing

  1. Fork the repository.
  2. Create your feature branch.
  3. Submit a pull request.

License

MIT License.