You must expose an internal procedures API and a semantic search index to multiple agents without hard-coding HTTP clients in every agent. The platform standard is Model Context Protocol (MCP). What design best integrates knowledge for multi-agent consumption?
Select an answer to reveal the explanation.
Short Explanation
C is the Foundry-era pattern. MCP lets you publish tools and knowledge sources once—search, procedures, whatever—and agents consume them as clients with scoped catalogs. Azure Functions, Logic Apps, and Azure API Management are common hosts/front doors for those servers. A stuffing keys into prompts is insecure and brittle. B centralizing raw DB credentials in the orchestrator creates a dangerous choke point and blocks specialist tooling. D email CSVs is not production knowledge integration. Remember the skill line: knowledge integration includes search, RAG, MCP-available sources, and semantic search.
Full Explanation
Correct Answer — C
Knowledge integration for multi-agent consumption includes search, RAG, MCP-available sources, and semantic search. MCP servers expose tools/knowledge; agents act as clients with scoped catalogs. Azure Functions, Logic Apps, and APIM are typical integration points.
Why A is wrong: Secrets in prompts and invented URLs violate security and reliability.
Why B is wrong: Raw DB credentials on the orchestrator break least privilege and specialist design.
Why D is wrong: Manual CSV email is not scalable multi-agent knowledge integration.
Exam tip: Prefer MCP (or equivalent tool protocol) over per-agent hard-coded clients.