Agent2Agent protocol
The Agent2Agent protocol (A2A) is an open standard that lets AI agents built on different frameworks and by different vendors find each other, delegate tasks and exchange results without exposing their internal tools or memory.
Also called: A2A
By Divya Sharma · Checked Nov 15, 2026 · How we review
Agents are being built on many stacks: LangGraph, CrewAI, Google ADK and custom code. A2A gives them a common way to talk. Google started the project and donated it to the Linux Foundation.
How it differs from MCP
The two are often confused. The Model Context Protocol connects one agent to tools, APIs and data. A2A connects an agent to other agents. A tool does what it is told and returns a result; another agent may plan, ask questions and work on a task over time. The A2A project suggests using both.
How it works
Each agent publishes a description of what it can do, so other agents can discover it. A client agent then sends a task, and the remote agent works on it and returns messages and results. The agents stay opaque to each other: neither needs to share its internal memory, tools or logic.
Example
A travel agent built on one framework hands the hotel search to a booking agent run by another company. It does not need to know which model or tools the booking agent uses, only how to send the task and read the reply.
When it matters
A2A is useful when agents cross team or company boundaries. Inside one application, a multi-agent system usually coordinates agents directly through agent orchestration.
Related terms
- Model Context Protocol
- The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools, data and prompts, using JSON-RPC messages between a host application, its clients and separate servers.
- Multi-agent system
- A multi-agent system is a setup in which several AI agents, each with its own instructions, tools and context, work on parts of a task and pass results to each other or to a coordinating agent.
- Agent orchestration
- Agent orchestration is the control of which agents or model calls run in an application, in what order, and how each next step is chosen, either by a model making the decision or by fixed code.
- AI agent
- An AI agent is a system in which a language model decides its own next steps: it calls tools, reads the results and repeats until the task is done, instead of following a fixed script.