Microsoft said it will support Google Cloud's Agent2Agent (A2A) standard in Azure AI Foundry and Copilot Studio.
Microsoft’s support for A2A likely means the enterprise software ecosystem will follow.
At Google Cloud Next, Google Cloud launched A2A, a communications standard that also has some big backers. A2A complement's Anthropic's Model Context Protocol (MCP). Both standards have gained wide support quickly since vendors need their various agents to work across platforms. Anthropic created MCP as an open standard for connecting AI assistants to systems where data lives. OpenAI and a bevy of others are backing MCP.
The promise of AI agents is that they can reason, navigate work and act autonomously. As Microsoft noted in its blog, "interoperability is no longer optional” because enterprises "want their agents to orchestrate tasks that span vendors, clouds, and data silos."
- Agentic AI: Everything that’s still missing to scale
- ServiceNow, UKG integrate AI agents across platforms
Microsoft said A2A support will be in Azure AI Foundry so enterprises can build multi-agent workflows across vendors, partners and infrastructure. Copilot Studio agents will extend beyond Microsoft's platforms.
The software giant said it will contribute to A2A as well as MCP. Microsoft also joined the A2A working group in GitHub.
