A team is building tool access for multi-agent solutions using Model Context Protocol. They want serverless scale, managed identity to backend APIs, and centralized governance. Which implementation approach best fits Azure-centric MCP tool hosting?
Select an answer to reveal the explanation.
Short Explanation
B matches the develop skill: design and build MCP servers/clients with Azure Functions, Logic Apps, and API Management patterns. Serverless MCP tool hosts scale, managed identity removes secret sprawl, APIM adds governance, and clients only see scoped tools. A, C, and D are security anti-patterns. When integrating tool ecosystems on Azure, prefer first-class MCP endpoints with identity-based access over shelling out with embedded passwords.
Full Explanation
B is correct because building tool ecosystems includes MCP servers and clients implemented with Azure Functions, Azure Logic Apps, and Azure API Management, using secure authentication and scoped exposure. A is incorrect: secrets in prompts and ad hoc curl calls lack lifecycle control and auditability. C is incorrect: shared admin RDP violates least privilege and is not a tool contract. D is incorrect: unauthenticated public tools invite abuse. Combine MCP tool schemas with result validation and error handling on the server side.