Microsoft and GitHub have formally joined the steering committee for the Model Context Protocol (MCP), a rising open standard pioneered by AI company Anthropic to streamline how artificial intelligence models connect with the tools and data they rely on.
The announcement was made during Microsoft’s Build 2025 developer conference on Monday, marking a strategic alignment between some of the biggest names in tech to boost interoperability in AI systems.
The move underlines Microsoft’s and GitHub’s growing investment in enabling developers to build more context-aware and enterprise-ready AI-powered applications. MCP has gained significant industry traction in recent months, with both OpenAI and Google pledging support earlier this year.
Register for Tekedia Mini-MBA edition 17 (June 9 – Sept 6, 2025) today for early bird discounts. Do annual for access to Blucera.com.
Tekedia AI in Business Masterclass opens registrations.
Join Tekedia Capital Syndicate and co-invest in great global startups.
Register to become a better CEO or Director with Tekedia CEO & Director Program.
What MCP Brings to the Table
MCP functions as a universal bridge between large language models (LLMs) and real-world data sources, from business software to content repositories and developer environments. The protocol enables two-way communication between AI models and the external systems they need to interact with, helping to execute tasks that require live or domain-specific data.
Developers using MCP can create “MCP servers” that expose data or functionalities, which can then be accessed by “MCP clients” — such as AI agents or chatbots — on demand. This setup allows models to move beyond static prompts and integrate more deeply with operational systems.
Microsoft said it plans to provide “broad first-party support” for MCP across several of its platforms, including Microsoft Azure and Windows 11.
“Developers will be able to wrap desired features and capabilities in their apps as MCP servers and make them available for Windows,” the company stated in its press materials.
Specifically, Microsoft will make system functionalities like File System access, Windowing, and Windows Subsystem for Linux (WSL) accessible to MCP-compatible models through Windows-based MCP servers.
Securing the Protocol and Expanding Capabilities
Beyond platform support, Microsoft revealed it has worked closely with Anthropic, other committee members, and the broader MCP community to improve the security and identity verification aspects of the protocol. A key development is a revised authorization specification that allows MCP-connected applications to securely access services like cloud storage, user profiles, and subscription data. This will enable end users to leverage trusted sign-in methods, such as Microsoft Account or enterprise identity providers, to authorize access to sensitive information in a controlled manner.
GitHub, meanwhile, is spearheading another critical addition to MCP’s infrastructure: a registry service. This service will serve as a directory for MCP servers, enabling developers to discover, manage, and integrate MCP server entries with ease. These registries can be configured as either public or private, depending on the use case and organizational requirements.
A New Standard for an Expanding AI Future
With its deep integration into GitHub Copilot, Microsoft Azure OpenAI Service, and Windows, MCP is poised to become a foundational protocol in the broader AI ecosystem. Microsoft’s CTO Kevin Scott likened MCP’s impact to the early days of the internet, recalling the surge of creativity it sparked in developers.
“This reminds me a lot of how things felt when I was a younger developer, when the internet was exploding into existence… I could grasp how each of these individual pieces worked and how they composed together, and I could just go play,” Scott said.
The protocol is not just about developer convenience. Its architecture and tooling aim to solve real-world enterprise challenges, from automating tasks across disconnected systems to powering AI assistants capable of navigating complex software environments. MCP unlocks the possibility of building AI systems that are deeply embedded in both user workflows and enterprise processes by enabling models to “understand” and “control” various applications through a standardized interface.
MCP’s growing list of supporters — including OpenAI, Google, Anthropic, Microsoft, and GitHub — highlights a broader industry push toward creating standard protocols for AI-human-computer interaction. Rather than each platform creating its own closed AI integrations, MCP invites a more modular and open approach.
Microsoft and GitHub are aligning themselves with the principle that AI development should be collaborative, secure, and interoperable by backing MCP and joining its steering committee. Their contributions not only enhance MCP’s core protocol but also bring the might of their developer ecosystems to its implementation.
The next few months are expected to bring further updates as Microsoft rolls out MCP features across Windows and Azure. With GitHub’s registry service and Microsoft’s security frameworks in place, developers could soon begin building MCP-enabled AI agents that interact with their operating systems and cloud environments in new and unprecedented ways.
However, as the race to build context-aware AI accelerates, MCP is fast becoming a foundational piece of the AI puzzle — and with Microsoft and GitHub now on board, its adoption is likely to accelerate across the tech industry.