Windows is getting support for the ‘USB-C of AI apps'
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.
'We want Windows as a platform to be able to evolve to a place where we think agents are a part of the workload on the operating system, and agents are a part of how customers interact with their apps and devices on an ongoing basis,' says Windows chief Pavan Davuluri in an interview with The Verge.
Microsoft is supporting MCP in a big way inside Windows, alongside even broader efforts to power what it calls the agentic web. To evolve Windows to this agentic world that Microsoft envisions, the company is introducing some new developer capabilities to enable this MCP framework for AI agents to expose key Windows functionality that AI agents will be able to access.
An MCP registry on Windows will act as the secure trustworthy source for all MCP servers that AI agents will be able to access. 'Agents can discover the installed MCP servers on client devices via the MCP Registry for Windows, leverage their expertise and offer meaningful value to end-users,' says Davuluri. MCP servers will be able to access things like the Windows File System, windowing, or the Windows Subsystem for Linux.
In a demo during a briefing for Microsoft's MCP in Windows announcement, the company showed me an early preview of how Perplexity on Windows could leverage MCP capabilities. Instead of having to manually select folders of documents, Perplexity can simply query the MCP registry to find a Windows file system MCP server to connect to. This allows Perplexity to perform file searches on behalf of a user in a more natural way, so you could simply say 'find all the files related to my vacation in my documents folder,' instead of having to add this folder or the documents manually.
You could imagine how a world of MCP servers and hosts inside Windows might eventually open the operating system up to a lot more automated app features, especially for querying data from the web inside apps like Excel. We're also starting to see Microsoft make parts of Windows AI-powered through AI agents. Copilot Plus PCs will soon have access to an AI agent settings interface, which lets you control system settings using natural language queries.
This type of MCP functionality also opens Windows up to a world of new attack methods from malicious actors. The security risks of MCP have been well documented in recent months, with warnings of potential token theft, server compromises, and prompt injection attacks. Microsoft is well aware of the security risks of embracing MCP at such an early stage, so the company is only making a preview available to select developers to help work on its feature set and secure it fully.
'I think we have a solid set of foundations and more importantly a solid architecture that gives us all the tools to start, to do this securely,' explains David Weston, vice president of enterprise and OS security at Microsoft, in an interview with The Verge. 'We're going to put security first, and ultimately we considering large language models as untrusted, as they can be trained on untrusted data and they can have cross-prompt injection.'
In the demo Microsoft showed me of MCP working in Windows, there were also early security prompts to let these AI apps access MCP capabilities. 'Just like a web app asks for your location, you're in control of what you share and we want to make sure that's intentional,' says Weston.
This is all early work from Microsoft right now, but the demo did remind me a little of Windows Vista's UAC prompts that would pop-up whenever you needed admin permissions to do things in Windows. Those became very annoying and a subject of mocking ads from Apple. Getting these prompts right will be key for Microsoft here, as they have to balance security and the convenience of using these AI agents and apps. I sure don't want a repeat of UAC or even Apple's copy / paste prompts that are highly irritating in iOS right now.
Microsoft is also committing to a variety of MCP security controls that Weston outlines in a blog post today, alongside some security requirements in order for MCP servers to appear in Microsoft's official list, or registry. 'These will prevent classes of attack like tool poisoning while also creating and open and diverseecosystem of MCP servers,' says Weston. 'More information on these requirements will be available when thedeveloper preview is released.'
Image: Microsoft
Alongside this big MCP push, Microsoft is also positioning its own AI platform inside Windows as the rebranded Windows AI Foundry. It integrates models from Foundry Local and other catalogs like Ollama and Nvidia NIMs, and is designed to allow developers to tap into models available on Copilot Plus PCs, or to bring their own models through Windows ML.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
3 minutes ago
- Yahoo
EliseAI raises $250 million in a16z-led round to expand in healthcare
By Krystal Hu (Reuters) -Enterprise software maker EliseAI has raised $250 million in a Series E funding round to expand its automation tools for the healthcare and housing industries, the company told Reuters. The latest funding values the company at over $2.2 billion, doubling its valuation from about a year ago. Venture capital firm Andreessen Horowitz led the round, with participation from Bessemer Venture Partners and existing investors such as Sapphire Ventures. Shop Top Mortgage Rates Personalized rates in minutes A quicker path to financial freedom Your Path to Homeownership The New York-based company, which builds AI to automate customer service and operations, said it surpassed $100 million in annual recurring revenue (ARR) earlier this year. The fresh capital will be used to fuel product innovation and double its roughly 300-person team over the next year, its CEO Minna Song told Reuters in an interview, with hiring plans across offices in New York, San Francisco, Boston and Chicago. The funding highlights investor appetite for so-called vertical AI companies that build deeply integrated, industry-specific solutions rather than general-purpose models. For EliseAI, the capital provides the firepower to deepen its hold on the real estate market and scale its newer healthcare division, tackling costly administrative tasks in two of the economy's largest and most complex sectors. "We've seen a fundamental shift in the market, from talking about AI to using it to solve really costly problems," Song said in an interview. "The demand from our customers was really strong, and so we decided that now is the time to invest in scaling." EliseAI's platform is able to automate the entire resolution process by focusing on specific industries, said Alex Immerman, partner at Andreessen Horowitz. "A vertical AI like ours will go really, really deep and will take that customer request and then handle every step that's required to resolve it," he said, including coordinating with vendors, scheduling, and ensuring compliance. The company started by targeting the housing industry in 2017, and expanded its applications to healthcare since 2022, an industry it said is burdened by similar communication friction and manual processes. With generative AI technology bursting onto the scene, its software can handle more complicated customer inquiries and workflows by integrating with models like the ones from OpenAI. It serves Zillow Group and other rental managers, and touts its technology is currently used in one in eight apartments in the U.S. In healthcare, the company has been focusing on outpatient specialties, including dermatology and women's health, integrating with electronic health record systems to automate administrative work. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
3 minutes ago
- Yahoo
US tech stocks hit by concerns over future of AI boom
US tech stocks sold off as warnings that the hype surrounding artificial intelligence could be overdone hit some of the year's Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Forbes
5 minutes ago
- Forbes
Curiosity: A Leadership Advantage AI Still Can't Replicate
AI can process millions of documents in the time it takes your team to open one. It writes memos, drafts code, and refines strategy in seconds. As AI reshapes decision making, the essential leadership focus shifts to amplifying what humans do best. That strength lies in curiosity—a disciplined practice of noticing what's missing, challenging assumptions, and exploring ambiguity even when moving forward quickly feels easier. What AI Misses AI recognizes patterns. It predicts based on what already exists. But it doesn't understand why something matters. It can't read the room. It won't ask if we're solving the right problem or just doing it faster. Curiosity fills that gap. It connects dots others miss. It shifts focus from urgency to significance. And when environments change quickly, that shift is critical. The biggest risk isn't choosing wrong. It's executing flawlessly in the wrong direction. Curiosity sharpens judgment. It reframes dissent. It makes leaders more coach than enforcer. It's a way of working that gets stronger with practice—and more valuable as AI gets better at everything else. How Curious Teams Work Curious teams test before declaring. They listen for the unspoken. They recover faster because they keep moving forward—not because they always knew where to go. When Satya Nadella took over at Microsoft, the company was confidently certain. He told his team to shift from 'know-it-all' to 'learn-it-all.' That shift wasn't branding. It cleared the path for a $13 billion OpenAI partnership and more than tripled the company's market value to $3.74 trillion as of mid-2025. At Amazon, Jeff Bezos built around what he called Day 1 mentality: stay curious, move fast, stay focused on long-term bets. It's how the company keeps launching billion-dollar businesses three decades in, with 2024 revenue at $638 billion. And in 2020 during a time of international crisis, Pfizer asked a different question: 'Why not this year?' Project Light Speed tore up standard timelines, tested mRNA approaches others overlooked, and delivered an authorized COVID-19 vaccine in nine months, shattering the previous four-year record. These successes highlight curiosity's power, yet many organizations struggle to sustain it. Why Curiosity Gets Squeezed Out Speed leaves no space. Metrics reward action over insight. And the more expertise we gain, the harder it becomes to ask naïve questions. Leaders don't mean to kill curiosity. But in environments built for output, questions start to feel like friction. How to Make Curiosity Operational Track it. Don't just celebrate wins. Track what questions got asked. End meetings by asking what stood out or was missed—like Nadella's cultural prompts. Fund exploration. Before greenlighting a project, ask: What assumption are we testing? Give teams the space to prove or disprove it, as Pfizer did with timelines. Schedule time to think. Block time—without deliverables—for learning and discussion. Use prompts. Keep devices out. Make it part of the job, not extracurricular, echoing Amazon's Day 1 mindset. Why This Matters Now AI will continue to outperform us at speed, recall, and precision. That gap will only grow. But it won't ask the question behind the question. It won't challenge a goal just because the world changed. It won't feel what customers feel—or care when something's missing. That's what people do. But only if we protect the conditions that make it possible. Curiosity is what keeps teams relevant when the rules change. It needs room to operate—and that's a leadership choice.
