Azure Data Explorer MCP Server logo

Azure Data Explorer MCP Server

by pab1it0

An MCP server for Azure Data Explorer/Eventhouse in Microsoft Fabric. It provides access to your clusters and databases through standardized MCP interfaces, allowing AI assistants to execute KQL queries and explore your data.

View on GitHub

Last updated: N/A

What is Azure Data Explorer MCP Server?

This is a Model Context Protocol (MCP) server designed to facilitate interaction with Azure Data Explorer (ADX) or Eventhouse in Microsoft Fabric. It enables AI assistants to query and explore data stored in ADX clusters using KQL.

How to use Azure Data Explorer MCP Server?

  1. Login to your Azure account with ADX permissions using Azure CLI. 2. Configure environment variables for your ADX cluster (ADX_CLUSTER_URL, ADX_DATABASE). 3. Add the server configuration to your client configuration file (e.g., for Claude Desktop), specifying the command to run the server and the required environment variables. You can also use Docker for deployment.

Key features of Azure Data Explorer MCP Server

  • Execute KQL queries against Azure Data Explorer

  • Discover and explore database resources (list tables, view schemas, sample data, get table statistics)

  • Authentication support (Token credential support)

  • Docker containerization support

  • Provide interactive tools for AI assistants

  • Configurable tool list

Use cases of Azure Data Explorer MCP Server

  • Enabling AI assistants to query and analyze data in Azure Data Explorer

  • Providing a standardized interface for accessing ADX data from various applications

  • Automating data exploration and discovery tasks

  • Integrating ADX data with AI-powered workflows

FAQ from Azure Data Explorer MCP Server

What is MCP?

MCP stands for Model Context Protocol, a standard for interacting with data sources.

How do I configure the server?

You need to set the ADX_CLUSTER_URL and ADX_DATABASE environment variables.

Can I use this with Docker?

Yes, the project includes Docker support for easy deployment.

What tools are available?

The server provides tools for executing queries, listing tables, getting table schemas, and sampling table data.

How can I contribute?

Contributions are welcome! Please open an issue or submit a pull request.