P730 min

MCP & Skills

An agent's capability layer has two halves. MCP gives the agent dynamic tools it can call at runtime. Skills give it injectable domain capability — instructions, references, and (when needed) bundled scripts, loaded on demand. This lesson covers both, and how they fit.

SDK FocuscreateSdkMcpServer()tool()mcpServersskillspluginssettingSources

The Capability Layer

Every production agent extends the base LLM along two orthogonal axes:

Capability layer: agent extended by MCP tools and Skills knowledgeAgent Capability LayerAgent (LLM + Loop)MCP — Dynamic ToolsSkills — Injected Knowledge & ScriptsExternal SystemsContext Window
AxisConcernPattern
What the agent can doRun actions, read data, call APIsMCP tools, resources, prompts
What the agent knowsBest practices, conventions, runnable recipesSkills (on-demand instructions + optional scripts)

Both can be added incrementally. Agents typically start with a few MCP tools, add domain skills as patterns crystallize, and grow toward a rich capability surface over time.

MCP: A Universal Tool Protocol

The Model Context Protocol (MCP) is an open standard introduced by Anthropic in November 2024. It defines a single, transport-agnostic protocol for AI applications to connect to external systems — replacing the per-LLM, per-app custom integration sprawl that came before.

Think USB-C for AI tooling: a shared protocol instead of a bespoke connector for every integration. MCP adoption is broad but still evolving:

Premium lesson preview

Continue with full access

This lesson stays here for preview. Full access unlocks the complete lesson, flashcards, and related practice.

Sign In to Unlock

One purchase unlocks advanced lessons, practice, and future updates.