October DealsAmazon USOctober deal check: compare before you payAmazon US: current deals, useful picks and tech finds.Check DealsClean PCRecommendedOne scan can reveal what keeps slowing WindowsLook for cleanup and repair opportunities.Run ScanOctober DealsAmazon USDeal season is back - check today's better picksAmazon US: current deals, useful picks and tech finds.See Picks×
Skip to content
World desk5 min

Exploring the Agent2Agent (A2A) Protocol with Spring AI

A2A enables independent agents to discover and delegate work across implementation boundaries. Spring AI developers can explore separate community projects for exposing an agent or invoking a remote one.
Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

A2A lets independently built agents discover and collaborate with one another through a defined protocol, without requiring them to reveal their private memory, tools, or implementation. For Spring AI developers, the surfaced ecosystem offers two distinct community paths: one to expose a Spring AI agent as an A2A server, and another to call remote A2A agents as subagents. Neither should be mistaken for built-in Spring AI core support.

What A2A does

The Agent2Agent (A2A) Protocol is an interoperability standard for agents built with different frameworks, languages, or vendors. A client interacts with an agent at its boundary: it can learn what the agent offers and request work without inspecting the agent’s internal state, memory, or tools. The A2A project’s specification page identifies version 1.0.0 as its latest released version; that protocol version is separate from the versions of Spring libraries that implement it. A2A specification

As an Amazon Associate I earn from qualifying purchases.

Discovery and work exchange

An Agent Card advertises an agent’s capabilities and connection information. A caller can use that information to decide whether and how to send a request. A2A models work as tasks, which may finish synchronously or continue asynchronously. Messages can carry text, files, or structured data rather than being limited to plain text.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Protocol-level communication options

The A2A project describes JSON-RPC 2.0 over HTTP(S), synchronous request/response, server-sent events (SSE) for streaming, and asynchronous push notifications. These are protocol-level capabilities, not a guarantee that a particular Spring integration implements every option. Check the chosen integration against the protocol version and the features your application needs. A2A project

Two Spring ecosystem paths, for different jobs

Goal Project What its documentation describes
Let other A2A clients call a Spring AI agent Spring AI Community spring-ai-a2a Server-side integration using an Agent Card, an AgentExecutor, and a Spring AI ChatClient; auto-configuration exposes A2A endpoints.
Delegate work from a Spring AI application to a remote A2A agent Spring AI Agent Utils A2A module A subagent integration using TaskTool to resolve an Agent Card, send JSON-RPC messages, wait for task completion, and extract text artifacts.

These are separate projects with separate purposes. Their documentation does not establish a complete compatibility matrix, and protocol support should not be taken to mean feature parity with A2A itself.

Expose a Spring AI agent as an A2A server

The Spring AI Community server repository’s quick start describes a setup in which the developer provides an Agent Card and an AgentExecutor backed by a Spring AI ChatClient. The README sample uses org.springaicommunity:spring-ai-a2a-server-autoconfigure:0.3.0; that is the sample’s version, not a claim that 0.3.0 is the latest release or is compatible with every current Spring AI version. Check the repository’s current guidance before adding a dependency.

What the server sample configures

  • Agent Card: name, description, URL, protocol version, capabilities, input and output modes, and skills.
  • AgentExecutor: the bridge between an incoming A2A task and the work performed by the Spring AI application.
  • ChatClient: the sample’s Spring AI model interaction, with an OpenAI model starter shown as an example.
  • Auto-configuration: the sample enables the server with spring.ai.a2a.server.enabled and demonstrates a card endpoint and a JSON-RPC sendMessage request.

Request flow described by the repository

  1. An A2A message controller receives the JSON-RPC request.
  2. The SDK request handler creates or manages the task.
  3. DefaultAgentExecutor bridges the request to the Spring AI ChatClient.
  4. The result is wrapped as a task artifact for the caller.

The sample also describes supplying agent tools through Spring AI’s @Tool support. This is the repository’s documented architecture, not an independently verified behavior or a guarantee that every protocol capability is implemented.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Call a remote A2A agent as a subagent

The separate spring-ai-agent-utils-a2a module is intended for the consuming side: a Spring AI application can delegate work to a remote A2A agent. Its README describes an A2ASubagentResolver that fetches an Agent Card and an A2ASubagentExecutor that calls the agent over JSON-RPC and extracts text from response artifacts. The module is shown registered alongside TaskTool.

The module README lists Java 17 or later and Spring AI 2.0.0 as requirements. Treat these as the documented requirements for that module, and verify them against the release you intend to use before integration. Its described text extraction should not be read as proof that every artifact type or A2A feature is exposed through the subagent API.

Choose based on the direction of the call

  • Choose the server integration when the goal is to make a Spring AI agent discoverable and callable by other A2A clients.
  • Consider the Agent Utils module when a Spring AI application needs to discover and delegate tasks to remote A2A agents.

Before selecting either project, check compatibility with the A2A version and Spring AI release you plan to use, discovery and endpoint behavior, task handling, any streaming requirement, and how authentication and endpoint protection will be implemented. The project descriptions establish the two different use cases, but do not provide a full feature-by-feature comparison.

Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Support on Ko-Fi

Is A2A part of Spring AI core?

The reviewed project documentation identifies the server integration and subagent module as community projects; it does not establish that A2A is built into Spring AI core. Spring AI issue #2911 records a maintainer comment from July 2025 saying the project was monitoring community progress, technical capabilities, and APIs before evaluating direct protocol support. Issue #6472, opened in June 2026, describes continued uncertainty about whether the community project would be integrated or remain the primary route. Neither establishes a definitive current roadmap or integration date. Spring AI issue #2911; Spring AI issue #6472

What’s actually slowing this PC down?

Pick the symptom - the matching free tool is one click away.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Version and deployment checks

  • Keep version numbers distinct: A2A 1.0.0 is the latest released specification version identified by the specification page; 0.3.0 is the version in the server README sample; the Agent Utils README lists Spring AI 2.0.0. These facts do not establish that those library versions are mutually compatible.
  • Verify exact coverage: confirm the endpoint names, message schema, task behavior, and streaming or notification support in the versions you select. The protocol’s feature list is not proof of support in either Spring integration.
  • Protect the deployment: the A2A project describes security, authentication, and observability as design considerations. That does not mean an application is secure by default; evaluate authentication, authorization, and access to exposed endpoints for your deployment.

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.

Leave a Reply

Your email address will not be published. Required fields are marked *

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

More from the Wire

  1. World desk4 min
    How to Spot an AI Voice Scam Before Sending MoneyDon’t rely on how a caller sounds. Pause, call back through a known number, and verify the emergency with another trusted person before sending money.
  2. Mountain View desk4 min
    Google’s SynthID Detector: How to Check AI-Generated Images, Video and AudioGoogle’s SynthID Detector looks for an embedded watermark in supported images, video and audio. Here is what its results do—and do not—show.
  3. Redmond desk20 min
    How to create a link to File or Folder in Windows 11Windows 11 gives you several ways to point to a file or folder without moving or duplicating it. You can create a desktop shortcut,…
Recommended PC Tool
Recommended PC Tool
Outdated Drivers Are Slowing You DownFree scan - exact matches
PC Slower Than It Used to Be?Free scan - under a minute

Two free Windows tools

One Free Minute Could Fix That PC

Before you go - each of these free tools takes about a minute and tackles what quietly slows a Windows PC down.

Special offer. View Outbyte info, uninstall instructions, EULA, and Privacy Policy.