A2A Agent Protocol Joins AAIF, Landing Alongside Anthropic's MCP
Google's Agent2Agent protocol has become a hosted project of the Linux Foundation's Agentic AI Foundation, placing it under the same governance as Anthropic's MCP standard.
Read more →This project is suspended: no new articles or editions will be published. The archive stays available.
The Agent2Agent Protocol (A2A) is an open standard that lets AI agents built by different companies discover each other and hand off tasks directly, without a shared codebase. It complements the Model Context Protocol (MCP), which connects an agent to its own tools, by instead connecting agents to one another. This hub follows A2A’s adoption and what it enables for multi-agent systems.
Google's Agent2Agent protocol has become a hosted project of the Linux Foundation's Agentic AI Foundation, placing it under the same governance as Anthropic's MCP standard.
Read more →
A2A is an open standard that lets AI agents from different companies find each other and hand off tasks directly — a different job from MCP, which connects an agent to its own tools.
Read more →