Two business units already run production specialist agents on different stacks. A new enterprise orchestrator in Microsoft Foundry must invoke those existing agents as tools/services without rewriting them from scratch, and must also expose enterprise knowledge sources through a standard tool interface. Which protocol approach should the architect specify?
Select an answer to reveal the explanation.
Short Explanation
The correct answer is B. Reuse existing specialists via A2A and wire knowledge/tools via MCP-style standard interfaces so Foundry can orchestrate without a ground-up rewrite. Collapsing everything into one prompt kills modularity. Ad hoc TCP and social DMs are not enterprise protocols.
Full Explanation
Option B is correct. Architecture and integration skills include specifying protocols for multi-agent communication and integrating existing agents with A2A and/or MCP, plus knowledge integration through MCP-available sources. That enables secure, structured interoperability without full rewrites.
Option A is incorrect because mandating a full rewrite into one prompt discards working specialists and modularity.
Option C is incorrect because unauthenticated ad hoc sockets lack standard security, schema, and operability for production multi-agent systems.
Option D is incorrect because public social channels are inappropriate for enterprise agent control paths and data.