mcp-kql-server
Verified Safeby 4R9UN
Overview
An AI-powered Model Context Protocol (MCP) server for executing Kusto Query Language (KQL) queries against Azure Data Explorer, including natural language to KQL (NL2KQL) conversion, intelligent schema discovery, caching, and data visualization.
Installation
python -m mcp_kql_serverSecurity Notes
The server leverages Azure CLI for authentication, which is a standard and secure practice. It uses `subprocess.run` to interact with `az login` and `az account get-access-token`, with proper input handling to mitigate injection risks. Schema memory is stored locally using SQLite, not exposed over the network. No usage of `eval` or obvious hardcoded secrets. The production deployment guide further emphasizes secure Azure Container Apps with Managed Identity.
Similar Servers
mcp-server-elasticsearch
Connects Model Context Protocol (MCP) clients to Elasticsearch, enabling natural language interaction with Elasticsearch indices and data.
mcp-foundry
A Model Context Protocol (MCP) server for Azure AI Foundry, providing a unified set of tools for interacting with Azure AI models, knowledge bases (AI Search), evaluation services, and finetuning operations.
tmcp
Build Model Context Protocol (MCP) servers for AI agents to interact with external tools and data sources, enabling LLMs to access context and perform actions.
powerbi-mcp
Enables AI assistants to interact with Power BI Desktop and Service for querying data, managing models, and performing safe bulk operations through natural language, ensuring enterprise-grade security and preserving report visual integrity during refactoring.