Tools and protocols

Agent2Agent Protocol (A2A)

stable definition
Machine-readable Download Markdown

Definition

The Agent2Agent Protocol, or A2A, is an open protocol for discovering and collaborating with independent agent services. An A2A client sends messages to a remote agent. The interaction may return a direct message or create a stateful task that produces status updates and artifacts over time.

The protocol is designed for agents that do not expose their internal memory, tools, or reasoning. Discovery happens through an Agent Card. Collaboration can be synchronous, streamed, or asynchronous, with task lookup, cancellation, subscriptions, and push notifications defined by the specification. Version and binding details can change, so implementations should record the protocol version they negotiated.

Interoperability stops at the trust boundary

A2A standardizes how systems communicate. It does not make agents equally capable, truthful, safe, or authorized. The server remains responsible for authorizing actions; the client remains responsible for deciding what data and authority it may delegate. Task state also does not create a shared organizational memory unless the applications build one.

Distinguish it from nearby terms

A2A connects independent agent services around messages, tasks, and artifacts. MCP connects an AI application to context and capabilities exposed by servers. An A2A agent may use MCP internally, and the protocols can coexist without replacing each other.

Check your understanding

Two agents speak A2A and one advertises a tax-filing skill. What has interoperability established? The message and task contract. Before delegation, verify identity, authorization, data policy, competence for the jurisdiction, and who owns an incorrect filing.

Also called

A2A, Agent-to-Agent Protocol

Factory areas

Public evidence