MCP Servers

Pluggable tools beyond the built-ins. Connecting your database, your Slack, your Linear.

MCP — Model Context Protocol — is the standard Claude Code uses to talk to external tools. Need the agent to query your Postgres? Hit your Linear tickets? Read your Notion? Each capability is an MCP server you add to the agent's toolbelt.

MCP servers are processes (local or remote) that expose tools the agent can call. The protocol is open and language-agnostic — you can write your own in an afternoon, and thousands are already published. Adding one is a single command — claude mcp add — and remote servers authenticate with OAuth via /mcp.

The mental model: built-in tools give the agent a terminal. MCP servers extend that terminal to your whole stack.

Check your understanding

Q1. What does MCP do?

· Score 100% on the quiz.

Vocabulary in this lesson

MCPModel Context Protocol: an open standard for plugging external tool servers into any agent harness.ToolA named capability the harness lets the model invoke, such as reading a file, running a shell command or fetching a page.AgentA model wired to tools and a loop: it reads, acts, checks the result, and goes again until the task is done or you stop it.

Plain-English definitions from the AI Coding Dictionary.