Microsoft to Integrate Google's A2A Protocol in Azure AI Foundry and Copilot Studio

Microsoft is embracing open AI agent collaboration with the upcoming integration of the Agent2Agent (A2A) protocol into its Azure AI Foundry and Copilot Studio. The move aims to support seamless interoperability between AI agents across platforms, clouds, and organisations.

"As agents take on more sophisticated roles, they need access not only to diverse models and tools but also to one another. That is why we are committed to advancing open protocols like Agent2Agent (A2A), coming soon to Azure AI Foundry and Copilot Studio, which will enable agents to collaborate across clouds, platforms, and organisational boundaries," Microsoft said in a blog post.

The protocol supports tools such as Semantic Kernel and LangChain and leverages Microsoft’s enterprise-grade safeguards, including Entra, Azure AI Content Safety, and mutual TLS.

With over 10,000 organisations using its Agent Service and 2.3 lakh adopting Copilot Studio—including 90% of Fortune 500 companies—Microsoft says interoperability is now essential for enterprise AI.

A public preview of A2A support is expected soon, with Microsoft also joining the A2A working group on GitHub to help develop the protocol further.

Agent2Agent (A2A) is an open interoperability protocol developed by Google to enable AI agents from different platforms, vendors, and environments to communicate, collaborate, and coordinate tasks securely and efficiently across systems.