A collection of official Microsoft MCP servers, providing AI assistant integration tools for various services such as Azure, GitHub, Microsoft 365, and Fabric. It supports local and remote deployment, helping developers connect AI models with various data sources and tools through a standardized protocol.

The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants

An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.

Office-Word-MCP-Server is a server based on the Model Context Protocol that provides a standard interface for AI assistants to create, read, and operate Microsoft Word documents, supporting rich document editing functions.

A Word document operation server based on the MCP protocol, providing AI assistants with the ability to create, edit, and manage Microsoft Word documents.

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.

Edit-MCP is a model context protocol server integrated with the Microsoft Edit tool, providing advanced file editing capabilities for AI systems and adopting a hybrid architecture that combines direct file operations and Edit integration.

This experiment guides users on how to deploy an MCP server and integrate it into Microsoft Copilot Studio. Through a standardized protocol, it connects AI models with data sources to achieve real - time data access and joke generation functions.

MS SQL MCP Server is a no-code bridge tool that allows AI assistants to directly query and explore Microsoft SQL Server databases. It supports database discovery, table structure viewing, secure execution of read-only SQL queries, and the generation of SQL from natural language.

A service for interacting with Microsoft To Do tasks via an AI assistant

Microsoft MCP Server for Enterprise is a publicly previewed server based on the Model Context Protocol that allows AI agents to access Microsoft Entra data through natural language queries and convert them into Microsoft Graph API calls, aiming to help developers and IT administrators integrate organizational data management into AI workflows.

The AutoGen MCP server is a multi - agent dialogue service integrating the Microsoft AutoGen framework, providing standardized interfaces for AI agent management and collaboration.

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.

mcp - searxng is an MCP server example designed for AI agents, which implements the external information search function through the open - source meta - search engine SearXNG. The project demonstrates how to integrate SearXNG and Microsoft's markdownify tool to convert web page content into Markdown - formatted text and communicate with MCP clients via the SSE protocol.

An MCP server integrated with the Microsoft Graph API, providing features such as Teams team collaboration, user management, and message search, and supporting AI assistants to interact with the Microsoft ecosystem through the protocol.

A Model Context Protocol (MCP) server implemented for Microsoft OneNote, providing a standardized interface for AI language models to interact with OneNote and supporting management functions for notebooks, sections, and pages.

UpTier is a desktop to - do application that combines the Microsoft To Do - style interface with the intelligent priority sorting function of Claude AI, enabling intelligent task management through the MCP protocol.

An MCP server based on Node.js and TypeScript for AI agents to interact with Microsoft SQL Server databases, providing table structure query and CRUD operation functions.

An MCP server implementation based on Spring Boot and Spring AI, enabling AI agents to search and navigate files and folders in Microsoft OneDrive.

A Model Context Protocol (MCP) server implemented for Microsoft OneNote, providing a standardized interface for AI language models to interact with OneNote and supporting management functions for notebooks, sections, and pages.

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 experiment guides users on how to deploy the MCP server and integrate it into Microsoft Copilot Studio, connecting AI models with data sources through a standardized protocol to achieve real-time data access and joke generation functions.

This project demonstrates how to integrate Model Context Protocol (MCP) tools with Microsoft Semantic Kernel to achieve seamless interaction between AI models and external data sources or tools. By standardizing the interaction between applications and AI models through the MCP protocol and combining the powerful functions of Semantic Kernel, developers can expand AI capabilities, dynamically call external functions, and simplify the orchestration of complex workflows.

This experiment guides users on how to deploy the MCP server and integrate it into Microsoft Copilot Studio. Connect AI models with data sources through a standardized protocol to achieve real - time data access and tool integration.

PictMCP is an MCP server that provides reliable and algorithmically correct pairwise test generation for software developers using AI assistants to design test cases. It runs Microsoft's PICT algorithm locally using WebAssembly, separating the AI's thinking from combinatorial mathematics calculations to ensure the determinacy and correctness of test generation.

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 Python-based automation tool that uses Google Gemini AI to control the Microsoft Paint program through natural language commands, enabling functions such as graphic drawing, text addition, and color management.

This project provides a complete solution for integrating Claude AI with the MCP server to access the Microsoft Graph API, including implementation guides for service setup, interface docking, and function customization in three stages.

Edit-MCP is a model context protocol server integrated with Microsoft Edit tools, providing advanced file editing functions for AI systems. It uses a hybrid architecture that combines file system operations and Edit integration.

This is an MCP server for Microsoft Dynamics 365 Finance & Operations development. It accesses over 50,000 F&O standard components through semantic search, enabling AI assistants to find relevant implementation patterns and read local source code during development.

A Python - based MCP server that allows AI agents to programmatically query the Microsoft 365 roadmap, helping organizations track upcoming feature updates for products such as Teams and SharePoint.

OneNote MCP Server is a service based on the Model Context Protocol that allows AI assistants to securely access and operate Microsoft OneNote data, providing functions such as reading, writing, searching, and editing, and supporting advanced content processing and verification.

MCPSharp is a .NET library for building servers and clients compliant with the MCP protocol. It supports quickly converting .NET methods into tool functions callable by AI models and provides integration with Microsoft.Extensions.AI and Semantic Kernel.

The MS SQL MCP Server is a no-code bridge tool that allows AI assistants to directly query and explore Microsoft SQL Server databases. It supports database discovery, table structure viewing, safe execution of read-only SQL queries, and the conversion of natural language to SQL.

A service that implements the Model Context Protocol (MCP), allowing AI language models such as Claude to interact with Microsoft OneNote, supporting access, creation, search, and summarization of note content.

An MCP server for Microsoft OneNote that allows AI agents to read, create, and analyze OneNote notebooks, sections, and pages, including automatically extracting text content from images through Claude Vision.

Office Whisperer v4.0 is an AI - based automation toolset for the Microsoft Office suite, providing 143 professional tools through a natural language interface to achieve comprehensive automated operations of Excel, Word, PowerPoint, and Outlook.