Microsoft Embraces Model Context Protocol (MCP) for AI Agents in Windows 11

Windows is getting support for the 'USB-C of AI apps'

Microsoft launched its Copilot Plus PC and Windows AI efforts last year, and now it's going a step further today with native Model Context Protocol (MCP) in Windows and the launch of the Windows AI Foundry. The groundwork is necessary for a future envisioned by Microsoft whereby automated AI agents assist their human companions. Introduced by Anthropic late last year, MCP is an open-source standard that's often referred to as the "USB-C port of AI" apps. Just as USB-C connects devices from many manufactures to a variety of peripherals, developers can use MCP to quickly let their AI apps or agents talk to other apps, web services, or even now parts of Windows. Microsoft's embrace of this protocol is a big part of its ambitions to reshape Windows and make it ready for a world of AI agents to be able to connect to apps and services in ways that haven't been possible before.

Microsoft goes all in on Anthropic's MCP standard for safer AI agent deployments

Also: What is Model Context Protocol? The emerging standard bridging AI and data, explained The company joined the MCP Steering Committee last week alongside GitHub, announcing support for the protocol across GitHub, Copilot Studio, Dynamics 365, Azure and Azure AI, Foundry Agents, Windows 11, and Semantic Kernel. On Monday, as part of the company's annual Build developer event, Microsoft announced two new initiatives to foster "secure, at-scale adoption" of MCP as developers build with agents across various platforms. "Windows 11 will support developers building intelligent applications that want to use MCP and generative AI capabilities to build applications centered around generative AI," Microsoft said, including autonomous agentic frameworks. The company will release the platform's new capabilities in preview for developers in the coming months. Also: The best VPN services (and how to choose the right one for you) Microsoft is embracing support for MCP across several of its widely used products, but only under the right conditions. "From a security perspective, the input and training data for a LLM are considered untrusted," Microsoft noted, adding that attacks on MCP servers can jailbreak AI chat apps or coax them to leak sensitive data. The company cited extensive research identifying several main security gaps AI agents can present, including poor credential management and a lack of proper security review. "The goal for Windows 11 as an agentic OS is to provide the strongest fundamental security capabilities while also evolving and adapting to emerging threats," Microsoft said in the release. To achieve that goal, Windows 11 will include features like proxy-mediated communication, tool-level authorization, and runtime authorization. Also: AI agents bring big risks and rewards for daring early adopters, says Forrester Joining forces with Anthropic and other parts of the MCP network, Microsoft has designed an authorization spec to improve security between apps and MCP servers. The new spec lets users implement verified sign-in methods like Microsoft Entra ID to let apps powered by agents and LLMs access data, including personal drives or subscriptions. "This is an important step toward enabling agent-based experiences in enterprise and consumer contexts where trust and accountability are essential," Microsoft said in the announcement. The move responds to the overall trend across industries of companies implementing agents for everything from lower-level customer support to more complex, multi-step workflow automations. Microsoft also announced a Windows registry service for MCP servers, which lets anyone "implement public or private, up-to-date, centralized repositories for MCP server entries and enable the discovery and management of various MCP implementations with their associated metadata, configurations, and capabilities," Microsoft explained. Also: Block's new open-source AI agent 'goose' lets you change direction mid-air Only MCP servers that meet the company's security threshold will make it onto the registry. The criteria include: Microsoft also announced NLWeb, a generally available "open project" that the company compares to HTML for "the agentic web," noting that its every endpoint is an MCP server. This approach means website admins can easily make their content accessible to AI agents. Also: 60% of AI agents work in IT departments - here's what they do every day Earlier this spring, tech giants Google and OpenAI also joined MCP. Microsoft's additions signal widening acceptance for open software and "shared infrastructure," as Microsoft called it, for the future of AI agents.

AI agents unleashed in Windows with Model Context Protocol - SiliconANGLE

Microsoft Corp. believes we're headed toward a future where artificial intelligence-powered agents will become pervasive in enterprise computing environments, so today it's making it easier for those agents to communicate with the third-party tools they must use to accomplish various tasks on behalf of their human users. At its annual developer conference, Microsoft Build 2025, the company today announced support for the popular open-source Model Context Protocol in Windows 11, providing a secure and standardized framework for AI agents to connect with native Windows applications. It says MCP support in Windows, available as a private developer preview, will act as a foundational layer for secure, interoperable agentic computing. It will help to expose the functionality of various applications to AI agents running on Windows 11 PCs. In a blog post, David Weston, Microsoft's corporate vice oresident of enterprise and OS security said the MCP capabilities are designed to ensure a secure and private experience with AI agents. MCP is a lightweight, open-source protocol developed by Anthropic PBC that allows AI agents to discover and invoke computing tools such as web browsers in a standardized way, providing seamless orchestration between local and remote services. It defines three roles, including the MCP Host, which refers to AI tools such as VS Code that need to access third-party tools; MCP Clients, which initiate requests to MCP Servers; and the MCP Servers, which are lightweight services that expose the specific capabilities of an application to the agentic tool via the MCP interface. With Windows 11, developers will be able to create more intelligent applications, leveraging MCP to take actions on behalf of users, the company explained. MCP Servers will be made available via the new MCP Registry, which is a single, secure and trustworthy source for AI agents to access MCP services on Windows. Agents will be able to discover and download installed MCP servers directly onto client devices, so they can interact with Windows system capabilities such as the file system and Windows Subsystem for Linux. Weston said Microsoft is putting a lot of emphasis on security with its implementation of MCP. The main guiding principle is one of "user control," he said, and the ability of AI agents to access MCP servers will be switched off by default. Once enabled, all sensitive actions performed by the AI agent on behalf of users will be fully auditable and transparent. MCP server access is also guided by the principle of least privilege and enforced by declarative capabilities and isolation, where application. This is to ensure that users always have full control over what privileges are granted to MCP servers, Microsoft said it's building MCP support for Windows in collaboration with companies including Anthropic, Figma Inc. and Perplexity AI Inc., which will all integrate their MCP capabilities for their Windows-based apps. Anthropic said in a statement that MCP support on Windows will give a substantial boost to a thriving ecosystem of integrations built by popular services. Microsoft also announced support for MCP across platforms including GitHub, Copilot Studio, Dynamics 365, Azure, Azure AI Foundry, Semantic Kernel and Foundry Agents. Having fully embraced the protocol, Microsoft - along with its GitHub unit - has also joined the MCP Steering Committee to help shape its future development. Already, they have made two key contributions to the MCP ecosystem. For instance, they have added a new identity and authorization specification that enables applications to connect to MCP servers in a more secure way. They can do so using Microsoft's Entra ID or another trusted sign-in method, so AI agents and LLM-powered applications can access data stored on personal storage drives and cloud subscription services. According to Microsoft, this is a key step toward supporting AI agent experiences in consumer and enterprise contexts, where accountability and trust are essential considerations. The other contribution is the MCP Registry, which allows anyone to implement public or private centralized repositories for MCP server entities. Both of the contributions are generally available now, the company said.

Microsoft Might Adopt Anthropic's MCP to Power Multiple AI Agents

Microsoft is reportedly planning to adopt Anthropic's Model Context Protocol (MCP) to let multiple artificial intelligence (AI) agents work together. As per the report, the Redmond-based tech giant said that it is focusing on multi-agent workflows and improved memory capability of its agents. The protocol standardises a way for AI chatbots to connect with external data hubs and retrieve information. The adoption of Anthropic's MCP standard could be announced at the Microsoft Build 2025, scheduled for Monday. Notably, the Build conference is aimed at developers building apps and tools on Microsoft's platform. The tech giant is now planning to standardise how its AI chatbots and agents connect to external data hubs. Citing Microsoft's Chief Technology Officer, Kevin Scott, Reuters reports that the company has a two-fold focus with its agents -- to make multiple agents work together, and for them to develop a long-term memory. Anthropic first introduced the MCP, a universal, open standard, in November 2024. The protocol aims to solve the problem of connecting AI systems with third-party data sources such as Google Cloud, Azure, and cloud-based customer relationship management (CRM) platforms. Since each data hub operates differently, the backend process of connecting with these sources and retrieving data is also different. With AI players using their standard protocol, there is no uniformity in how the data is retrieved and processed, resulting in disparity in inference time as well as the final output. MCP provides a single protocol to let AI systems connect to these knowledge sources and access the data. Scott reportedly said that Microsoft is focused on adopting standards across the technology industry to enable AI agents made by different developers to collaborate and work together. On MCP, Scott reportedly highlighted that the protocol can help the company create an "agentic web" similar to how hypertext protocols in the 1990s helped in spreading the Internet. The Microsoft CTO reportedly also highlighted improving the memory function of AI agents to make them more useful. Most AI agents available publicly have enough memory to carry out the task assigned in a single prompt. While it can both provide comprehensive answers (Deep Research tools by OpenAI and Google), and execute tasks on the web (OpenAI's Operator), it lacks the context from one task to another. Microsoft is reportedly building a new approach dubbed structured retrieval augmentation. This system allows an AI agent to extract a small portion of information from each turn in a conversation with a user to gain the context of the series of tasks it performed in a session. It is expected that Microsoft will detail this approach, as well as how AI agents developed on its platform will follow MCP.

Microsoft Build 2025: Windows 11 to Get MCP Support for AI Agents

The goal is to make Windows 11 an agentic OS. Initially, it will be available to developers for feedback purposes only. Today, at the Build 2025 event, Microsoft announced that native MCP (Model Context Protocol) support is coming to Windows 11. In case you are unaware, MCP is an open standard that allows AI models to communicate with external data, API, or services. MCP has been introduced by Anthropic to leverage the power of AI with external data. It can be used to enable AI agents on Windows 11. David Weston, Microsoft's VP of OS Security, writes, "Windows 11 will support developers building intelligent applications that want to use MCP and generative AI capabilities to build applications centered around generative AI and intelligence which can leverage MCP where appropriate to take actions on behalf of the user." While introducing MCP on Windows 11, Microsoft is also emphasizing to improve security. For a secure agentic architecture, Microsoft is working on several threat vectors such as Cross-Prompt Injection, Authentication Gaps, Credential Leakage, Tool Poisoning, and more. In addition, Microsoft says, "Only MCP servers which meet a baseline security criteria will be available in the Windows Registry." The company also noted that principle of least privilege will be enforced to minimize the impact of any possible attack using an MCP server. Finally, the private preview of MCP integration into Windows 11 will be available to developers after the Build event for feedback purposes.