The A2A Protocol
As agents proliferate, they need to talk to each other. A2A (Agent-to-Agent), launched by Google in April 2025 and subsequently donated to the Agentic AI Foundation (AAIF) under the Linux Foundation, is an open standard enabling agents from different vendors (e.g., an OpenAI agent and a Claude agent) to collaborate securely. As of 2026, A2A is backed by 150+ supporting organizations including Google, Salesforce, SAP, Deloitte, and more.
A2A systems include:
- Agent Cards: Standardized metadata describing an agent's capabilities, skills, and contact endpoints. Signed Agent Cards add cryptographic verification to ensure the card was published by the claimed organization, preventing impersonation and enabling trust in agent discovery.
- Tasks & Artifacts: Structured work items that agents exchange to coordinate actions securely.
- Agent Discovery: "Is there an agent on this network that can book a flight?"
- Capabilities Exchange: Agents share their JSON tool schemas.
- Handoffs: Transferring context and control from Agent A to Agent B.
💡 Key Insight: Think of MCP as Agent-to-Database/Tool, and A2A as Agent-to-Agent. Together, they form the full interoperability stack. Both are now governed by the Linux Foundation.