mcpField
1
1. Background

1. Background

Local
github.com/nitishsharma25Databases0Updated 82w ago
Repository

About 1. Background

A sample Kusto MCP server paired with a terminal chat client, for conversational queries about data in a Kusto cluster. It uses AzureOpenAI and Azure CLI authentication for Kusto access.

Key features

  1. 01Conversational Kusto queries
  2. 02AzureOpenAI-backed chat
  3. 03Azure CLI authentication

Use cases

  1. 01Ask questions about Kusto cluster data
  2. 02Explore data through terminal chat

MCP support

The server works with an MCP client in the sample chat app to answer queries using Kusto data.

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

1. Background

This Chat app can answer kusto queries in conversational manner. In the backend, it uses the MCP Client/Server framework and AzureOpenAI's LLM.

2. Prerequisites

  • Python
  • pip
  • Azure OpenAI's parameters

3. Setup environment

az login

Current code uses Az CLI authentication for connection to kusto, so perform the above step before running the app.

Clone the repo, activate virtual environment and install dependencies for client and server:

git clone <this repo>
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 inside kusto-mcp-client directory and add the following variables:
  • Go to the Azure OpenAI Service page in Azure AI Foundry portal.
  • Find them as mentioned in the picture below:
AZUREOPENAI_API_KEY       = ""
AZUREOPENAI_ENDPOINT      = ""
AZUREOPENAI_API_VERSION   = ""
AZUREOPENAI_MODEL         = ""

parameters

4. How to run sample project

From Inside kusto-mcp-client dir, run the below command:

python main.py "../kusto-mcp-server/main.py"
  • Enter your queries in the terminal as show in this picture and start chatting

parameters

  • To start a new session, enter quit and start the client again

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.