Agent2Agent Protocol

Google's open standard for AI agent interoperability, enabling autonomous systems to discover each other, negotiate tasks, and collaborate while keeping proprietary logic opaque.

Agent2Agent (A2A) is an open protocol launched by Google in April 2025 that provides a standardized way for AI agents from different vendors to communicate. It includes three layers: discovery via Agent Cards (JSON manifests describing capabilities), authentication via OAuth 2.0 and OpenID Connect, and communication via JSON-RPC over HTTPS. The protocol structures work around Task objects and maintains agent opacity, meaning collaborating agents never expose their internal logic or training data. Now governed by the Linux Foundation's Agentic AI Foundation, A2A complements Anthropic's MCP by handling agent-to-agent communication while MCP handles agent-to-tool integration.

Also known as