A2A Protocol
definition
The Agent-to-Agent (A2A) protocol, introduced by Google, defines a standard for how independent AI agents communicate and collaborate with each other to complete complex tasks. While MCP standardizes how agents connect to tools and data, A2A standardizes how agents connect to other agents — enabling scenarios where a coding agent delegates a research task to a specialized research agent, or a planning agent coordinates multiple execution agents.
The Agent-to-Agent (A2A) protocol, introduced by Google, defines a standard for how independent AI agents communicate and collaborate with each other to complete complex tasks. While MCP standardizes how agents connect to tools and data, A2A standardizes how agents connect to other agents — enabling scenarios where a coding agent delegates a research task to a specialized research agent, or a planning agent coordinates multiple execution agents. The protocol defines capabilities like agent cards (discovering what an agent can do), task management (assigning and tracking multi-step work), and message passing (structured communication between agents). A2A is still early but represents an important evolution in the agent ecosystem, where the unit of composition shifts from tools to entire autonomous agents. This concept connects to MCP overview for the tool-level protocol that A2A complements, multi-agent architectures for the patterns that A2A enables at scale, and orchestrator-worker for the coordination model most relevant to A2A.