iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
A2A lets independently built AI agents discover and collaborate with one another through a shared protocol, without exposing their private memory or tool implementations. For Spring AI developers, the current paths described by project documentation are distinct: Spring AI Community’s spring-ai-a2a project exposes a Spring AI agent as an A2A server, while the separate Spring AI Agent Utils A2A module calls remote A2A agents as subagents. Neither should be described as built into Spring AI core.
What A2A does
Agent2Agent (A2A) is an open protocol for communication among independent agents, including systems built with different frameworks, languages, or vendors. Rather than requiring one agent to inspect another’s internal state, memory, or tools, A2A lets a caller interact with the agent through an advertised capability and a defined message/task boundary. The A2A project describes the protocol as supporting discovery and collaboration while preserving each agent’s implementation autonomy.
The protocol documentation describes JSON-RPC 2.0 over HTTP(S), Agent Card discovery, synchronous requests, streaming with server-sent events (SSE), asynchronous push notifications, and exchange of text, files, and structured JSON. These are protocol-level capabilities, not a promise that every library integration implements all of them. Check the protocol version and the chosen Spring project’s feature coverage before relying on a particular endpoint, message format, streaming mode, or notification flow.
Quick wins for a faster PC:
Scan for outdated or missing drivers - takes under a minuteDriver Scan →Repair Windows errors before they cause bigger problemsFix Now →Agent Cards and tasks
An Agent Card advertises an agent’s identity, connection information, capabilities, and supported skills. A client can use that information to decide whether the remote agent is relevant and how to contact it. An interaction may finish in a request/response exchange or continue as a task, depending on the work and the implementation.
#1 Best Overall
The A2A specification page surfaced here identifies version 1.0.0 as the latest released specification. That is a protocol version, not a Spring library version; consult the specification and the library documentation together when checking compatibility.
Which Spring AI A2A path fits your goal?
| Goal | Project | What its documentation describes |
|---|---|---|
| Let other A2A clients call a Spring AI agent | spring-ai-a2a from Spring AI Community |
Server-side integration using an Agent Card, an Agent Executor, 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, a separate Agent Utils module |
Subagent resolution and invocation through TaskTool, including Agent Card resolution and JSON-RPC messaging. |
The projects document different roles, not a complete side-by-side compatibility matrix. Before choosing, check protocol-version compatibility, discovery and endpoint behavior, the task and streaming features you need, authentication and endpoint protection, and the project’s current maintenance and release status.
Expose a Spring AI agent as an A2A server
The Spring AI Community spring-ai-a2a repository documents a server integration. Its quick start uses org.springaicommunity:spring-ai-a2a-server-autoconfigure:0.3.0; that is the sample’s dependency version, not a claim that it is the latest available release. The example also uses an OpenAI model starter, but the relevant server pattern is to describe the agent and provide an executor backed by a Spring AI ChatClient.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Repair Windows errors before they cause bigger problems3Scan for outdated or missing drivers - takes under a minuteConfiguration and request flow
- Add the server integration. Follow the repository’s current quick start for the compatible artifact and version. The documented sample uses
org.springaicommunity:spring-ai-a2a-server-autoconfigure:0.3.0; verify release compatibility before copying it into a new project. - Define the Agent Card. The sample card includes the agent’s name, description, URL, protocol version, capabilities, input and output modes, and skills. These declarations help clients discover the agent and understand what it advertises.
- Provide an Agent Executor. The repository’s example bridges incoming work to a Spring AI
ChatClient. It also shows Spring AI@Toolsupport for tools available to the agent. - Enable the server. The sample sets
spring.ai.a2a.server.enabledto enable the integration, then demonstrates an Agent Card endpoint and a JSON-RPCsendMessagecall. Use the repository’s documented endpoint and request schema for the version you install.
As described by the repository, the message controller receives a JSON-RPC request; the SDK request handler creates or manages the task; and DefaultAgentExecutor passes the request to the Spring AI ChatClient. The returned content is wrapped as a task artifact. This is the project’s account of its architecture, not an independent compatibility or performance test.
Call a remote A2A agent as a subagent
The separate spring-ai-agent-utils-a2a module is for using remote A2A agents from a Spring AI application. Its README lists Java 17 or later and Spring AI 2.0.0 as requirements; check the module’s current instructions before selecting versions for a project.
How the documented subagent flow works
A2ASubagentResolverresolves a remote agent’s Agent Card.A2ASubagentExecutorinvokes that agent using JSON-RPC.- The executor waits for task completion and extracts text from response artifacts.
- The README shows the subagent being registered alongside
TaskTool.
This documentation describes a text-extraction flow; it does not establish that the module exposes every A2A protocol feature, such as streaming, file exchange, or push notifications. Check the module’s own compatibility and feature documentation if your application depends on those behaviors.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Is A2A built into Spring AI core?
The reviewed project and issue documentation does not establish A2A as a built-in Spring AI core feature. Spring AI issue #2911 records a maintainer comment from July 2025 saying the team 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. These discussions do not settle the current roadmap; they are not a commitment to a future integration date.
For implementation today, treat the server integration and the Agent Utils subagent module as separate projects outside the Spring AI core feature set, and verify their current releases and compatibility rather than assuming core support.
Security and compatibility checks
The A2A project describes the protocol as designed with security, authentication, and observability in mind. That design intent does not make a deployed endpoint secure by default. Evaluate authentication, authorization, network exposure, and endpoint protection for the specific Spring integration and deployment you use.
Quick Recap
- Confirm the library’s supported A2A version and compare its endpoint and message schema with the protocol version your other agent uses.
- Verify which capabilities the chosen integration actually implements; protocol-level streaming or file support does not prove support in a Spring module.
- Review how remote Agent Cards are discovered and how their advertised URLs are trusted and protected in your environment.
- Check task completion, error handling, and any required streaming or asynchronous behavior against the project documentation.
- Use release documentation for exact dependency versions; the server README’s 0.3.0 sample and the Agent Utils README’s Spring AI 2.0.0 requirement are separate version statements, not a compatibility guarantee between the modules.
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.
