Model Context Protocol (MCP)
Comes up in: AI engineering, AI system design
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- why MCP (one protocol for tools/data across apps)
- hosts, clients, servers
- server features (tools, resources, prompts) and client features (elicitation)
- transports (stdio, Streamable HTTP)
- stateless requests in the current revision (facts)
- authorisation (OAuth)
- extensions (Tasks, MCP Apps)
Words you will know
What you will practise
- build an MCP server exposing the site's glossary (TS SDK v2:
@modelcontextprotocol/server)
Interview questions this answers
- What is MCP and what problem does it solve?
- What are the security risks of connecting an agent to third-party MCP servers?