Azure Data Explorer (Kusto) MCP server

Azure Data Explorer (Kusto) MCP Server allows you to interact with your Kusto databases and tables through the Model Context Protocol. This server acts as a bridge between MCP-compatible tools like VS Code and your Azure Data Explorer clusters, enabling easier data analysis and exploration with natural language interactions.

Installation

Follow these steps to install and configure the MCP server:

git clone https://github.com/abhirockzz/mcp_kusto
cd mcp_kusto

go build -o mcp_kusto main.go

Configuration

Setting Up in VS Code

To configure the MCP server in VS Code:

1. Create a mcp.json file with the following content:

{
  "servers": {
    "Kusto MCP server": {
      "type": "stdio",
      "command": "enter path to binary e.g. /Users/demo/Desktop/mcp_kusto",
      "args": []
    }
  }
}

Setting Up in Claude Desktop

For Claude Desktop, use this configuration format:

{
  "mcpServers": {
    "Kusto MCP server": {
      "command": "enter path to binary e.g. /Users/demo/Desktop/mcp_kusto",
      "args": []
    }
  }
}

Authentication

The MCP server uses DefaultAzureCredential for authentication, which provides a secure way to connect to your Azure resources:

1. The server looks for credentials in environment variables or locally installed developer tools
2. You can simply authenticate by running az login with the Azure CLI
3. Ensure your user principal has permissions for .show databases, .show table, .show tables, and query execution

Using the MCP Server

Once configured, you can use the following tools through your MCP-compatible client:

Available Tools

• list_databases: Lists all databases in your Azure Data Explorer cluster
• list_tables: Shows all tables in a specific Azure Data Explorer database
• get_table_schema: Retrieves the schema of a specific table
• execute_query: Runs read-only KQL queries against your database

Usage Examples

You can interact with these tools through natural language in VS Code's Copilot or other MCP-compatible interfaces. For example:

• "Show me all the databases in my Azure Data Explorer cluster"
• "List the tables in the 'SampleDB' database"
• "What's the schema for the 'Events' table in 'SampleDB'?"
• "Run a query to show the top 10 records from the 'Events' table"

Important Notes

Always validate the results and queries before making decisions based on them, as LLMs can sometimes make mistakes in their interpretations or query generation.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.