MCP Servers and Subagent Orchestration

Connecting agents to external systems, and scaling one agent into many

Understand why the Model Context Protocol exists and how an MCP server extends what an agent can see and do, why that access model demands more careful trust and credential design than local file edits, and how subagents let you decompose a task across isolated context windows — sequentially for context hygiene, or in parallel for wall-clock speed — with git worktrees keeping concurrent writers from clobbering each other.

Practice questions (12)

• Scoping Credentials for a New MCP Server

  Advanced
  View →

• Deciding When a Subagent Is Worth It for a Single Task

  Advanced
  View →

• Parallel Fan-Out: Wall Clock vs. Token Cost

  Advanced
  View →

• Diagnosing a Clobbered Refactor

  Advanced
  View →

• Designing a Multi-Agent Review Pipeline for a Large PR

  Advanced
  View →

Quizzes (1)