Answer at least 13 out of 15 questions correctly to earn your certificate. Questions are randomly selected from a larger bank - each attempt is different.
1.How does the SSE transport work differently from stdio?
2.What does "destructive: true" annotation on a tool indicate?
3.Why must you never write to stdout in an MCP stdio server?
4.When should you use an MCP Resource instead of a Tool?
5.What makes a well-designed MCP tool description important?
6.What does "openWorldHint: false" in a tool annotation mean?
7.What is the difference between static and dynamic MCP resources?
8.In JSON-RPC 2.0, what distinguishes a Notification from a Request?
9.What is an MCP Prompt primitive used for?
10.In stdio transport, where should server logs and debug output be written?
11.What validation library does the course recommend for MCP tool parameters?
12.Who controls when each MCP primitive is invoked?
13.What is the "single responsibility" principle for MCP tools?
14.What message format standard does MCP use?
15.What is the key advantage of Streamable HTTP over SSE transport?