Skip to main content
LESSON 1 of 5//Agentic CLI & MCP

What is MCP (Model Context Protocol)?

The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Think of it as a USB port for AI — a universal way to plug capabilities into language models.

Why MCP matters

Without MCP, AI agents are limited to their training data. With MCP, they can read your files, query databases, call APIs, and interact with your development environment in real-time — all through the command line.

MCP works through a client-server architecture. An MCP server exposes tools and resources. An MCP client (like Claude Desktop or an IDE) connects to those servers and uses their capabilities.

MCP architecture overviewzsh // interactive
┌─────────────────────────────────────────┐
│ AI Application (Claude, IDE, etc.) │
│ └── MCP Client │
│ ├── MCP Server: filesystem │
│ ├── MCP Server: database │
│ └── MCP Server: custom-tools │
└─────────────────────────────────────────┘

Each MCP server can expose tools (functions the AI can call), resources (data the AI can read), and prompts (templates the AI can use). The CLI is how you install, configure, and run these servers.

PRACTICE//Try the commands from this lesson
INTERACTIVE_TERMINAL//sandbox
Practice terminal — try the commands from this lesson!
Type 'help' for available commands. Tab completion not available in simulator.
Try: