Claude now works across Microsoft 365 apps, reading emails and summarizing chats

Anthropic has linked its Claude artificial intelligence (AI) assistant to Microsoft 365, allowing business users to seamlessly pull information from emails, documents, and team chats.

The connection went live in mid-October 2025 for Claude Team and Enterprise subscribers. Claude now reads content from Microsoft Outlook, Teams, SharePoint, and OneDrive. Workers can ask questions and get answers drawn from multiple sources at once.

Company administrators must turn on the feature before employees can use it.

“Claude works with the productivity tools you use every day, bringing context from your documents, emails, and calendar directly into your conversations,” Anthropic wrote in a blog post. “Spend less time gathering information and more time on the decisions and work that drive impact.”

Source: Anthropic

The AI can summarize email threads, track project updates from Teams conversations, and retrieve files from SharePoint. Users no longer need to upload documents manually.

Anthropic also launched Enterprise Search, which scans across all connected company apps simultaneously. An employee asking about remote work policies might receive information from HR documents, internal emails, and team guidelines in one response.

The feature aims to help with onboarding new staff and analyzing customer feedback patterns. “Enterprise search is particularly valuable for onboarding new team members, answering strategic questions like analyzing patterns in customer feedback, and quickly identifying the right internal experts to consult on any topic,” Anthropic said.

Administrators must set up which apps Claude can access before teams use the search function.

For this integration to work, Anthropic used its Model Context Protocol (MCP), an open-source standard for linking AI systems to external data sources. Microsoft has adopted MCP across Windows as it builds what it calls “AI PCs.”

The partnership between Microsoft and Anthropic has grown closer in recent months. Anthropic’s models already power several Microsoft tools, including Copilot Researcher, GitHub Copilot, and a new Office Agent.

This move is part of Microsoft’s strategy to work with multiple AI providers rather than relying solely on OpenAI. The company now offers businesses a choice between different AI assistants within the same productivity suite.

Anthropic recently completed a funding round that valued the company at $183 billion, cementing its position as a major player in workplace AI.