Agent2Agent

The Agent2Agent (A2A) protocol is an open standard, announced by Google in April 2025, that defines how independent AI agents communicate and coordinate with one another across different systems, vendors, and frameworks.

As organizations build more agentic systems, they increasingly need agents built by different teams — and on different platforms — to work together. Without a common protocol, every agent-to-agent integration is bespoke. A2A addresses this fragmentation by giving agents a standard way to discover each other, exchange messages, and delegate tasks, without sharing internal state or relying on proprietary integrations.

A2A is complementary to the Model Context Protocol (MCP), not a competitor to it. The two solve different problems: MCP connects an agent to its tools and data sources, while A2A connects agents to other agents. A single system often uses both — MCP to give each agent its capabilities, and A2A to let those agents collaborate.

Core concepts

  • Agent Card — A metadata document, exchanged over HTTP in a JSON-based format, that describes an agent’s capabilities and how to reach it. Agent Cards allow agents to discover one another and understand what each can do.

  • Tasks — The unit of work that one agent delegates to another. A client agent sends a task to a remote agent, which carries it out and returns results.

For security, A2A supports Transport Layer Security (TLS), JSON Web Tokens (JWTs), and OpenID Connect for authentication and authorization between agents.

Governance

In June 2025, Google transferred A2A to the Linux Foundation for vendor-neutral governance. At the time of the announcement, more than 100 technology companies had pledged support, and Microsoft stated plans to integrate A2A into its AI platforms. This mirrors the path taken by MCP, which was likewise moved to a Linux Foundation fund — part of a broader industry effort to reduce fragmentation and vendor lock-in across AI agent ecosystems.

The agent-to-agent space has since consolidated around A2A. IBM Research launched a parallel standard, the Agent Communication Protocol (ACP), in March 2025 to power its open-source BeeAI platform, donating both to the Linux Foundation that same month. In August 2025, ACP joined forces with A2A under the Linux Foundation: the ACP team wound down active development and contributed its technology to A2A, and BeeAI itself migrated to A2A. A2A is now the de facto open standard for inter-agent communication.

See also