Agent-to-Agent (A2A) Protocol
Agent-to-Agent (A2A) Protocol is a standardized communication framework that enables AI agents to interact, coordinate, and collaborate with each other in multi-agent systems. A2A was introduced by Google in April 2025 and donated to the Linux Foundation in June 2025, which now hosts the specification and its SDKs. It defines how an agent publishes its identity and capabilities in an Agent Card, how another agent addresses it over JSON-RPC 2.0 on HTTP(S), and how a unit of work moves through a task lifecycle, with Server-Sent Events carrying incremental updates for long-running tasks. The goal is interoperability between agents built by different vendors and on different frameworks, so that one agent can delegate work to another without sharing a runtime or internal memory. A2A is positioned as complementary to the Model Context Protocol: MCP connects an agent to tools and data sources, while A2A connects agents to each other.
Related terms
Related services: Single-agent system development, Agentic AI consulting.
Ready to put agentic AI to work?
Book a free 45-minute consultation. We'll map one real process worth automating with production-grade AI.