Lokka is a server based on the Model - Context - Protocol (MCP) for querying and managing Azure and Microsoft 365 tenants by operating Microsoft Graph and Azure RM APIs through natural language.

This project demonstrates how to integrate an AI agent powered by Azure OpenAI with the Microsoft Fabric data warehouse through the Model Context Protocol (MCP), using GraphQL as a common data connection layer to achieve bidirectional access to enterprise data.

A service that interacts with Microsoft To Do tasks through an AI assistant, requiring a Node.js environment and Azure application registration for authentication configuration.

A Python-based MCP server project that integrates Microsoft Security Copilot and Microsoft Sentinel, supports KQL query execution, skill set management, and security prompt running, and uses Azure authentication.

The distributed MCP server provides an API toolset for legal information query, weather data, Azure pricing, and utility functions, supporting AI assistants such as Microsoft Copilot to call through the MCP protocol.

This project showcases multiple Model Context Protocol (MCP) servers integrated with Microsoft Azure, which enable large language models (LLMs) to securely access Azure tools and data sources, including AI agent services and various database services.

A KQL query server based on the Microsoft cloud platform that supports executing Azure Data Explorer queries through Azure CLI authentication.

This project demonstrates how to deploy an MCP server protected by Entra ID on Azure, obtain Microsoft Graph tokens in a passwordless manner through the on-behalf-of flow, and implement it using API management and Azure functions.

An Azure Cloud PC management server based on the Microsoft Graph API, providing functions such as user list query and Cloud PC management (restart, rename, troubleshooting, etc.)