This repository provides an MCP server for Azure Data Explorer, enabling AI assistants to execute KQL queries and explore data through standardized interfaces. It supports authentication, resource discovery, and Docker containerization.
A Model Context Protocol (MCP) server for Azure Data Explorer, enabling AI assistants to interact with your data through KQL queries. It provides a standardized MCP interface to access Azure Data Explorer clusters and databases.
Features: Execute KQL queries, discover database resources (list tables, view schemas, sample data), and supports token credential authentication. It also supports Docker containerization for easy deployment. The server offers configurable tools, allowing you to select the functionalities exposed to the MCP client.
Usage: Requires Azure CLI login and ADX cluster configuration via environment variables. The server configuration can be added to client configuration files like Claude Desktop. Docker usage is supported through docker run
or docker-compose
.
Development: Contributions are welcome. The project uses uv
for dependency management. A comprehensive test suite is included, covering configuration, server functionality, error handling, and main application logic.
pab1it0/adx-mcp-server
March 10, 2025
March 27, 2025
Python