🌟 Microsoft MCP Servers

🧭 MAOS v1 Governance (Activ8-AI Fork)

This fork operates under MAOS v1 (Modular Automation Operating System) governance framework, which establishes:

• Tier 3 Repository Classification: Full governance controls with automated agent workflows
• Charter Compliance: All changes must align with Charter Standards for security, modularity, and provider-agnostic design
• Fail-Closed Enforcement: Required governance checks must pass before merge
• Human Authority: All merges require explicit human approval
• Audit Trail: Comprehensive logging and compliance tracking

Fork-Specific Governance

This is an Activ8-AI maintained fork of Microsoft MCP.

Upstream Synchronization:

• Regular syncs with upstream Microsoft MCP repository
• Activ8-AI specific modifications tracked separately
• Governance requirements apply to Activ8-AI changes only

Contribution Guidelines:

• Upstream contributions should be made to the original Microsoft repository
• Activ8-AI specific features require governance approval
• See main repository Activ8-AI/mcp for governance details

For complete governance documentation, see:

• Main Repository: Activ8-AI/mcp - Primary governance standards
• Upstream: microsoft/mcp - Original project
• MCP Protocol: modelcontextprotocol.io - Official protocol
• Azure MCP Docs: learn.microsoft.com/azure/developer/azure-mcp-server
• Fabric Docs: learn.microsoft.com/fabric

High-Risk Powers

This Microsoft MCP server repository has specific governance requirements:

• Azure MCP Server:

  • Full Azure cloud resource access
  • Azure Resource Manager (ARM) operations
  • Azure service management and configuration
  • Subscription-level operations
  • Resource group management
  • Azure credentials and authentication

• Microsoft Fabric MCP Server:

  • Fabric workspace access
  • Data pipeline operations
  • Lakehouse management
  • Notebook execution
  • Data warehouse operations
  • Fabric API authentication

• MCP Protocol Implementation:

  • Host application integration
  • Client-server architecture
  • Context provision to LLMs
  • Tool and capability exposure
  • Multi-service orchestration

• Engineering Infrastructure:

  • Build pipelines and automation
  • Release management
  • Testing frameworks
  • Documentation generation
  • Contributor tooling

• Cloud Operations:

  • Azure resource creation/deletion
  • Cost implications of operations
  • Security configuration changes
  • Network and access policies
  • Data storage and retrieval

All high-risk operations are:

• Gated behind required human approval
• Logged for audit compliance
• Subject to automated security scanning
• Governed by principle of least privilege
• Require secure credential management

Security Notes

• Azure Credentials: Never commit Azure service principal credentials or connection strings
• Fabric Tokens: Protect Microsoft Fabric API tokens and authentication
• Service Principals: Use least-privilege service principals for Azure access
• MCP Security: Secure MCP server endpoints and client connections
• Resource Access: Limit Azure resource access to required operations only
• Cost Monitoring: Track Azure resource usage and costs
• RBAC: Implement proper role-based access control for Azure operations
• Audit Logging: Enable comprehensive Azure activity logging
• Token Rotation: Regularly rotate service principal credentials
• Production Separation: Use separate credentials for dev/staging/production
• Network Security: Configure network security groups and firewalls
• Data Protection: Implement encryption at rest and in transit
• Compliance: Ensure Azure operations meet regulatory requirements
• Subscription Limits: Monitor Azure subscription quotas and limits

📘 What is MCP?

Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs). It allows AI applications to connect with various data sources and tools in a consistent manner, enhancing their capabilities and flexibility. MCP follows a client-server architecture:

• MCP Hosts: Applications like AI assistants or IDEs that initiate connections.
• MCP Clients: Connectors within the host application that maintain 1:1 connections with servers.
• MCP Servers: Services that provide context and capabilities through the standardized MCP.

For more details, visit the official MCP website.

📁 Which MCP Servers are built from this repository?

This repository contains core libraries, test frameworks, engineering systems, pipelines, and tooling for Microsoft MCP Server contributors to unify engineering investments; and reduce duplication and divergence:

MCP Server	README	Source Code	CHANGELOG	Releases	Documentation	Troubleshooting	Support
Azure MCP	Azure MCP README	Azure MCP Source Code	Azure MCP CHANGELOG	Azure MCP Releases	Azure MCP Documentation	Azure MCP Troubleshooting	Azure MCP Support
Microsoft Fabric MCP	Fabric MCP README	Fabric MCP Source Code	Fabric MCP CHANGELOG	Fabric MCP Releases	Fabric Documentation	Fabric MCP Troubleshooting	Fabric MCP Support

📚 Which MCP Servers are available from Microsoft?

Azure

• REPOSITORY: microsoft/mcp
• DESCRIPTION: All Azure MCP tools in a single server. The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. Azure MCP Server can be used alone or with the GitHub Copilot for Azure extension in VS Code.
• CATEGORY: CLOUD AND INFRASTRUCTURE
• TYPE: Local
• INSTALL:

✨ Azure AI Foundry

• REPOSITORY: azure-ai-foundry/mcp-foundry
• DESCRIPTION: A Model Context Protocol server for Azure AI Foundry, providing a unified set of tools for models, knowledge, evaluation, and more.
• CATEGORY: CLOUD AND INFRASTRUCTURE
• TYPE: Local
• INSTALL:

Azure DevOps

• REPOSITORY: Azure DevOps MCP Server - Public Preview
• DESCRIPTION: This TypeScript project provides a local MCP server for Azure DevOps, enabling you to perform a wide range of Azure DevOps tasks directly from your code editor.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

☸️ Azure Kubernetes Service (AKS)

• REPOSITORY: Azure/aks-mcp
• DESCRIPTION: An MCP server that enables AI assistants to interact with Azure Kubernetes Service (AKS) clusters. It serves as a bridge between AI tools and AKS, translating natural language requests into AKS operations and returning the results in a format the AI tools can understand.
• CATEGORY: CLOUD AND INFRASTRUCTURE
• TYPE: Local
• INSTALL:

GitHub

• REPOSITORY: github/github-mcp-server
• DESCRIPTION: Access GitHub repositories, issues, and pull requests through secure API integration.
• CATEGORY: DEVELOPER TOOLS
• TYPE: REMOTE - https://api.githubcopilot.com/mcp
• INSTALL:

GitHub Awesome-Copilot

• REPOSITORY: github/awesome-copilot
• DESCRIPTION: Community-contributed instructions, prompts, and configurations to help you make the most of GitHub Copilot.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

📝 Markitdown

• REPOSITORY: microsoft/markitdown
• DESCRIPTION: A specialized MCP server for Markdown processing and manipulation. Enables AI models to read, write, and transform Markdown content with robust parsing and formatting capabilities.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

💻 Microsoft 365 Agents Toolkit

• REPOSITORY: OfficeDev/microsoft-365-agents-toolkit
• DESCRIPTION: The Microsoft 365 Agents Toolkit MCP Server is a Model Context Protocol (MCP) server that provides a seamless connection between AI agents and developers for building apps and agents for Microsoft 365 and Microsoft 365 Copilot.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

📊 Microsoft Clarity

• REPOSITORY: microsoft/clarity-mcp-server
• DESCRIPTION: This is a Model Context Protocol (MCP) server for the Microsoft Clarity data export API. It allows you to fetch analytics data from Clarity using Claude for Desktop or other MCP-compatible clients.
• CATEGORY: DATA AND ANALYTICS
• TYPE: Local
• INSTALL: microsoft/clarity-mcp-server

🗃️ Microsoft Dataverse

• REPOSITORY: Microsoft Dataverse
• DESCRIPTION: Chat over your business data using NL - Discover tables, run queries, retrieve data, insert or update records, and execute custom prompts grounded in business knowledge and context.
• CATEGORY: DATA AND ANALYTICS
• TYPE: Local
• INSTALL: Microsoft Dataverse

💻 Microsoft Dev Box

• REPOSITORY: @microsoft/devbox-mcp
• DESCRIPTION: An MCP server for Microsoft Dev Box. Enables natural language interactions for developer-focused operations like managing Dev Boxes, configuring environments, and handling pools.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

Microsoft Fabric (Public Preview)

• REPOSITORY: microsoft/mcp
• DESCRIPTION: A local-first MCP server providing AI agents with comprehensive access to Microsoft Fabric's public APIs, item definitions, and best practices. Enables AI-assisted development for all Fabric workloads without connecting to live environments.
• CATEGORY: DATA AND ANALYTICS
• TYPE: Local
• INSTALL: microsoft/mcp

🛢️ Microsoft Fabric Real-Time Intelligence

• REPOSITORY: RTI MCP Server
• DESCRIPTION: This server enables AI agents to interact with Fabric RTI services by providing tools through the MCP interface, allowing for seamless data querying and analysis capabilities.
• CATEGORY: DATA AND ANALYTICS
• TYPE: Local
• INSTALL:

📁 Microsoft Files

• REPOSITORY: microsoft/files-mcp-server
• DESCRIPTION: Provides a declarative control plane for managing file-based resources, supporting AI workflows that involve static files and documentation synchronization.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL: microsoft/files-mcp-server

📚 Microsoft Learn

• REPOSITORY: microsoftdocs/mcp
• DESCRIPTION: AI assistant with real-time access to official Microsoft documentation.
• CATEGORY: PRODUCTIVITY
• TYPE: REMOTE - https://learn.microsoft.com/api/mcp
• INSTALL:

🛢️ Microsoft SQL

• REPOSITORY: MSSQL MCP Server
• DESCRIPTION: Chat with your business data the new agentic way using natural language and AI. Connect to any SQL database—from ground (on-premises) to Azure cloud to Microsoft Fabric via a simple connection string. Discover and define table schemas, manage tables, and perform CRUD operations through conversational prompts.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL: MSSQL MCP Server

💻 NuGet MCP Server

• REPOSITORY: NuGet/Home
• DESCRIPTION: This is a Model Context Protocol (MCP) server for NuGet, enabling advanced tooling and automation scenarios for NuGet package management.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL: Nuget MCP Server

🎭 Playwright

• REPOSITORY: microsoft/playwright-mcp
• DESCRIPTION: This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
• CATEGORY: DEVELOPER TOOLS
• TYPE: Local
• INSTALL:

🏗️ Looking for starter templates that use MCP?

Check out the Azure Developer CLI (azd) templates tagged with MCP.

📎 Related Resources

• Microsoft MCP Resources
• MCP Pattern Overview
• MCP SDKs and Building Blocks
• MCP Specification

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.