Claude Code glossary

The terms we use to rate tools, explained with links to Anthropic’s docs.

MCP server

The Model Context Protocol (MCP) is an open-source standard for connecting AI tools to external systems. An MCP server exposes a service’s tools, data and APIs so Claude Code can read and act on that system directly instead of working from text you paste in.

Claude Code plugin

A Claude Code plugin is a directory of skills, agents, hooks, MCP servers or other components that Claude Code installs and loads as one unit.

Skill

A skill is a SKILL.md file with instructions that Claude adds to its toolkit. Claude uses a skill when it is relevant, or you can invoke one directly with /skill-name.

Hooks

Hooks are user-defined shell commands, HTTP endpoints, MCP tool calls, LLM prompts or subagents that run automatically at specific points in Claude Code’s lifecycle.

Subagents

Subagents are specialized AI assistants that handle specific types of tasks. Each runs in its own context window with a custom system prompt, specific tool access and independent permissions.