Your team must expose an internal pricing calculator to multiple agents as a governed tool. Developers prefer a lightweight serverless implementation that can be reached through Model Context Protocol clients. Which implementation approach best fits Azure multi-agent tool ecosystems?
Select an answer to reveal the explanation.
Short Explanation
Tools should be real services, not prompt folklore. You host the pricing calculator as an MCP server on Azure Functions or comparable Azure compute, authenticate clients, and let agents call it through MCP clients. Rate changes update one service, not every prompt.
Full Explanation
AI-500 expects designing and building MCP servers and clients, including Azure Functions, Logic Apps, and API Management patterns. The MCP server hosted on Azure Functions or similar Azure compute, exposing the calculator as a tool and called by agents through authenticated MCP clients, is the governed tool path. Hard-coding the pricing formula into every agent system prompt duplicates logic and breaks single-source-of-truth pricing. Emailing a spreadsheet for OCR is not machine-actionable or reliable. Opening RDP access for UI clicking is an anti-pattern for reliability and security. Apply tool scopes, auth, and result validation around the MCP tool. Exam tip: MCP is how agents discover and invoke tools/resources consistently across a multi-agent estate.