GitHub and Microsoft Embrace Anthropic's MCP Standard for Connecting AI Models to Data

In a significant development for the AI industry, GitHub and Microsoft have announced that they are joining the steering committee for Anthropic's Model Connector Protocol (MCP) standard. This protocol enables AI models to directly access and interact with data sources like business tools, software, content repositories, and app development environments.

The announcement, made at Microsoft's Build 2025 conference, highlights the growing momentum behind MCP. Earlier this year, both OpenAI and Google said they would support the protocol in their respective AI products.

MCP allows developers to build two-way connections between data sources and AI-powered applications, such as chatbots. Developers can expose data through "MCP servers" and build "MCP clients" - apps and workflows - that connect to those servers on demand.

Microsoft and GitHub say they will deliver "broad first-party support" for MCP across their platforms and services, including Microsoft Azure and Windows 11. This will include integrating MCP capabilities directly into Windows, allowing developers to expose app functionalities as MCP servers that AI models can interact with.

Additionally, Microsoft's identity and security teams have collaborated with Anthropic and the MCP community to design an updated authorization spec. This will enable more secure connections between MCP-powered apps and data sources, using trusted sign-in methods.

On the GitHub side, the company has worked with the MCP steering committee to create a registry service. This allows developers to implement public or private centralized repositories for MCP server entries, facilitating the discovery and management of different MCP implementations.

The embrace of MCP by industry giants like Microsoft and GitHub underscores the growing importance of this standard in the AI ecosystem. By providing seamless connectivity between AI models and a wide range of data sources, MCP has the potential to unlock new use cases and accelerate the adoption of AI-powered applications across enterprises and beyond.