A2A protocol joins the Agentic AI Foundation alongside MCP

In one sentence On August 20 the transfer of Google A2A protocol to the Agentic AI Foundation was announced, the neutral Linux Foundation-directed body that already hosts MCP: the agent protocol layer consolidates under a single governance backed by every major cloud and model lab.

Needs review Official source

ShareLinkedIn X

For AI agents from different companies to work together they need a common language. Over the past two years two main ones emerged: Anthropic MCP, which connects an agent to its tools and data, and Google A2A, which lets an agent discover other agents and delegate tasks to them.

On August 20 it was announced that A2A formally joins the Agentic AI Foundation, the neutral organization tied to the Linux Foundation that already hosts MCP. In practice, the two key protocols of the agentic ecosystem now sit under the same roof, with governance independent from any single vendor.

Nothing visibly changes for users tomorrow morning, but the move matters: it is the same path Linux and Kubernetes took, technologies born inside one company and then entrusted to neutral foundations to become everyone's standard. AWS, Anthropic, Google, Microsoft and OpenAI are among the signatories of the governance model: the industry's fiercest rivals agree at least on the ground rules their agents will use to talk to each other.