Northwind Traders is integrating an existing inventory specialist agent built by another team with a new customer-service orchestrator. The inventory agent already exposes skills over a standard agent-to-agent interface. The orchestrator also needs to call a warehouse REST API for stock counts. Which protocol assignment is most appropriate?
Select an answer to reveal the explanation.
Short Explanation
You've got two different integration problems, so you need two different contracts. Use Agent2Agent (A2A) to bring the existing inventory specialist agent into the multi-agent solution, and use Model Context Protocol (MCP) or tool/function interfaces for the warehouse REST API. Blob drops, swapped protocol roles, and prompt-stuffed credentials aren't production answers.
Full Explanation
AI-500 covers specifying appropriate protocols for multi-agent communication and integrating existing agents using A2A and/or MCP. The correct assignment uses Agent2Agent (A2A) for agent-to-agent integration of an existing specialist and Model Context Protocol (MCP) or tool/function interfaces for structured external system access — the correct separation of concerns.
The proprietary JSON files dropped in Azure Blob Storage approach is incorrect: asynchronous blob handoffs lack typed discovery, capability negotiation, and reliable request/response semantics needed for production agent coordination.
The swapped MCP/A2A assignment is incorrect because it reverses the roles. MCP is designed for tool and context resource access; A2A targets agent interoperability. Using MCP as the primary agent-to-agent fabric and A2A for raw REST is inverted.
The prompt-embedded credentials approach is incorrect and insecure. Credentials must not live in prompts, and models should not freestyle HTTP without mediated tool boundaries, auth, and validation.
Exam tip: A2A connects agents; MCP (and function tools) connect agents to tools/data sources.