Search

What are you looking for?

Search our services, use cases and practical insights.

Enter at least 2 characters

Popular starting points

Agents and automation

What is the Agent2Agent protocol (A2A), and how does it complement MCP?

When agents operated by different teams, products or vendors need to work together, an internal function call is often no longer enough. A2A provides a shared language for that boundary, but it does not remove the need to design the process and enforce security controls.

The short answer

The Agent2Agent protocol, or A2A, is an open standard for communication and task delegation between independent AI agents. An agent can discover another agent's capabilities through its Agent Card, exchange messages, track long-running tasks and receive results as artifacts. MCP complements A2A at a different layer: MCP connects an agent to tools and context, while A2A connects agents to one another.

In brief

  • A2A v1.0 is the first stable version of the open protocol and supports bindings including HTTP+JSON, JSON-RPC and gRPC.
  • Agent Card, Message, Task and Artifact are its central domain objects.
  • Polling, streaming and push notifications support both short and long-running work.
  • A2A defines communication and security mechanisms, but does not make an agent connection inherently trustworthy or safe.

Which building blocks does A2A use?

A2A treats the remote agent as an independent service. The calling agent does not need to know its internal prompts, models or tools. It sees a published description of capabilities instead and exchanges standardised objects with it.

The Agent Card is a self-description, not an automatic trust guarantee. In A2A v1.0 it can be signed, but the surrounding platform still needs to verify provenance, signature, freshness and the capabilities that are actually permitted.

Agent Card
Describes an agent's identity, endpoints, supported protocol versions, capabilities, skills and advertised security schemes.
Message
Carries an input, clarification or response between client and agent. Content can contain multiple parts such as text, files or structured data.
Task
Represents stateful work that can take time, require clarification or be cancelled.
Artifact
Is an output produced by the agent, such as a report, file or structured dataset. An intermediate result must remain distinguishable from a final one.

How does an A2A interaction work?

A short request can be answered immediately with a Message. If it becomes longer-running work, the agent returns a Task with status and later updates. The protocol therefore supports not only synchronous request and response, but also incremental and asynchronous processing.

  1. Step 1

    Discover the capability

    The client reads an Agent Card and verifies its version, endpoint, advertised skills, security schemes and trustworthiness.

  2. Step 2

    Send the assignment as a Message

    Goal, context and permitted data are transmitted as narrowly and structurally as possible. Authorisation is enforced outside free-form message text.

  3. Step 3

    Receive a Message or Task

    A short answer may return directly. Longer work creates a Task with a unique identifier and traceable state.

  4. Step 4

    Receive progress

    Depending on duration and infrastructure, the client uses polling, a streaming channel or push notifications and handles retries idempotently.

  5. Step 5

    Review and accept Artifacts

    Outputs are validated, associated with their Task and agent version, and only then passed into a downstream process.

How do A2A, MCP and a normal API differ?

The three approaches are not necessarily competitors. They solve different integration problems. One architecture may combine a domain API as a reliable system boundary, MCP for controlled tool use within an agent and A2A for delegation between independent agent services.

How do A2A, MCP and a normal API differ?
Building blockConnectsSuitable forNot its responsibility
A2AIndependent agents across system or organisational boundariesDiscovering capabilities, delegating work and exchanging status and resultsNot domain authorisation or a replacement for internal process controls
MCPAn AI application or agent with a server's tools, resources and templatesA consistent way to access exposed capabilities and contextNot general coordination between independent agents
Domain APISoftware components through explicit endpoints and data contractsStable, testable system actions and queries with clear semanticsNot flexible goal negotiation or agentic task execution
Internal function callComponents within the same applicationTight, fast integration under one control boundaryNot an interoperable boundary for independent vendors or teams

When is A2A worthwhile, and when is it not?

A2A becomes useful when two agents are operated independently, implemented differently or owned by separate organisations. Within a single application, the protocol often adds more complexity than value. Stable, fully specified data exchange is usually simpler and more testable through a normal API.

  • Useful: a procurement agent delegates a supplier check to a separately governed compliance agent.
  • Useful: agents from different vendors need to collaborate across a shared, versioned boundary.
  • Useful: work is long-running and needs status, clarifications or multiple result artifacts.
  • Usually unnecessary: one agent merely calls database, search or email tools; MCP or a direct API often fits better.
  • Usually not ideal: a deterministic system process already has a stable API contract and needs no open-ended task delegation.

Which controls does enterprise A2A require?

TLS, security schemes and signed Agent Cards provide technical foundations, but they do not replace a trust decision. The receiving agent must authenticate every caller and authorise it for the specific resource and action. Even a correctly identified partner should receive only the minimum data and capabilities needed.

A2A v1.0 adds version negotiation and multiple bindings. Organisations should still define permitted versions and extensions, test compatibility and plan a controlled migration route. Protocol version, agent version from the Agent Card, Task, identity, approvals and Artifacts all belong in one traceable record.

Which controls does enterprise A2A require?
ControlConcrete implementationFailure case to test
Identity and authenticationVerify server certificate and Agent Card provenance; authenticate the client with an appropriate method such as OAuth 2.0 or mTLSAn unknown or impersonating agent presents a familiar Agent Card
Authorisation and least privilegeEnforce rights by tenant, skill, data type and action; never forward broad user rights by defaultA legitimate agent requests data outside its assignment
Data minimisationTransfer only required Message parts and Artifacts; classify and filter sensitive fieldsAn intermediate result includes unnecessary customer data or credentials
LoggingCorrelate Task history, status changes, caller identity, approvals, versions and result acceptanceAn Artifact cannot later be linked to its assignment and accountable party
Versioning and failureDefine supported versions, run contract tests and control timeouts, cancellation and retriesAn update changes field semantics or a retry executes an action twice
Example from day-to-day business

Example: supplier screening across two agent systems

A procurement agent turns a request into a structured screening assignment. It discovers the approved compliance agent through its signed Agent Card and sends only supplier ID, country, screening purpose and deadline. The compliance agent creates a Task, requests missing information and later returns a report as an Artifact. The procurement agent may display the result but cannot override a block. Identities, versions, status changes and human approval are logged. Direct ERP postings continue to use a tightly scoped domain API.

What to remember

Use A2A where independent agents truly need to exchange assignments and results. Use MCP for tools and context and domain APIs for stable system actions, and treat every agent boundary as a regular security-critical service integration.

Sources and further reading

These primary sources provide further detail on definitions, technical foundations or responsible use.

Content reviewed

Would you like to apply this to your situation?

Together, we clarify what makes sense for your process, data and systems – in plain language and without unnecessary complexity.

Discuss Your Project