Azure Data Explorer MCP server

This is a small helper that connects your AI assistant to Azure Data Explorer, Microsoft's service for storing and searching large amounts of data. Once it is set up, you can ask your AI questions about your data in plain words and it will run the query for you. It is handy for anyone who works with an Azure Data Explorer database but does not want to write queries by hand.

What this MCP server does

You ask your AI a question about your data, like how many rows a table has or what a table looks like. The AI sends that request to this helper program. The helper signs in to your Azure Data Explorer cluster and runs a KQL query, which is the query language Azure Data Explorer uses. The results come back and the AI turns them into a plain answer in your chat. You never have to open the Azure portal or write the query yourself.

Click to zoom

What you can do with it

• Run KQL queries against your Azure Data Explorer database
• List all the tables in your database
• Show the columns and types for a specific table
• Preview a few rows of sample data from a table
• Get table details like row counts and storage size
• Explore an unfamiliar database before you write reports

Try asking your AI

• “List all the tables in my Azure Data Explorer database”
• “Show me the schema of the Events table”
• “Give me 10 sample rows from the Logs table”
• “Run this KQL query and summarize the results: Events | count”

What it gives back to you

You get answers in your chat, not raw files. For a query, you get the rows back, usually as a short table or a summary the AI writes for you. For discovery, you get lists of tables, column names and types, a few sample rows, or numbers like row counts and storage size. The AI can then explain or reshape those results however you like.

Before you start

Who it's for

Anyone who works with an Azure Data Explorer or Kusto database and wants to ask questions in plain words instead of writing KQL by hand.