Agentic architecture, MCP & Claude Code

20% of the exam

Agent patterns, the Model Context Protocol (MCP) and Claude Code workflows.

Thinking in agents

  • Agent = loop: perceive → decide → act (tool use) → observe → repeat until a stop.
  • Simple, well-described tools; too many hurts. Clear stop criteria + iteration cap.
  • Break tasks down (orchestration, sub-agents) rather than one mega-prompt.

Model Context Protocol (MCP)

  • Open standard to connect Claude to data/tools via MCP servers (tools, resources, prompts).
  • A server exposes capabilities; a client (Claude Desktop, Claude Code, app) consumes them. Transports: stdio (local), HTTP/SSE (remote).
  • One server serves many clients — write the integration once.

Claude Code

  • Terminal coding agent: reads/writes files, runs commands, uses tools + MCP servers.
  • Best practices: CLAUDE.md (project context), tool permissions, task decomposition.

Practice — 10 questions

0/10 answered
  1. 1. What is MCP (Model Context Protocol)?
  2. 2. Two typical MCP server transports?
  3. 3. An agent loop spirals (endless tool calls). Fix?
  4. 4. Why expose an integration via an MCP server vs ad-hoc wiring?
  5. 5. Give persistent project context to Claude Code?
  6. 6. In MCP, which primitive exposes actions the model can execute?
  7. 7. When prefer a coded deterministic workflow over an autonomous agent?
  8. 8. Why craft a tool's description carefully?
  9. 9. Suitable pattern to break a complex task into coordinated subtasks?
  10. 10. Security best practice for a production Claude Code agent's tools?

← Back to the Academy · Mock exam →