Mysql Kusto MCP

🚀 Chat Application for Kusto Query

This chat application can answer Kusto queries in a conversational form. It leverages the MCP client/server framework and Azure OpenAI's Large Language Model (LLM) in the backend.

🚀 Quick Start

✨ Features

• The chat application can answer Kusto queries in a conversational form.
• It uses the MCP client/server framework and Azure OpenAI's LLM in the backend.

📦 Installation

Prerequisites

• Python
• pip
• Parameters for Azure OpenAI

Set up the environment

First, use Az CLI authentication to connect to Kusto:

az login

Since the current code uses Az CLI authentication to connect to Kusto, please execute the above step before running the application.

Clone the repository and install the dependencies for the client and server after activating the virtual environment:

git clone <this repository>
virtualenv .venv
.venv/scripts/activate
pip install -r kusto-mcp-client/requirements.txt
pip install -r kusto-mcp-server/requirements.txt
cd kusto-mcp-client

Create a .env file in the kusto-mcp-client directory and add the following variables:

• Go to the Azure OpenAI Service page in the Azure AI Foundry portal.
• Find these parameters as shown in the following image:

AZUREOPENAI_API_KEY       = ""
AZUREOPENAI_ENDPOINT      = ""
AZUREOPENAI_API_VERSION   = ""
AZUREOPENAI_MODEL         = ""

💻 Usage Examples

Basic Usage

To run the sample project, from the kusto-mcp-client directory, run the following command:

python main.py "../kusto-mcp-server/main.py"

• Enter your query in the terminal to start chatting, as shown in the following image:

• To start a new session, type quit and restart the client.