Every term in the Claude ecosystem
9 bilingual definitions with practical examples, install paths and cross-references. Designed for developers landing in the Claude ecosystem.
MCP (Model Context Protocol)
An open standard for AI assistants to communicate with external tools, databases, APIs, and data sources through a unified JSON-RPC interface.
MCP Server
A program that implements the Model Context Protocol to expose tools, resources, or prompts to Claude and other AI assistants.
Claude Skill
A reusable bundle of instructions, examples, and context that Claude loads on demand to perform a specific task.
Subagent
A specialized agent Claude Code can spawn to handle a focused task in isolation, with its own system prompt, tools, and context window.
Claude Code
Anthropic's official CLI that lets Claude read, write, and execute code in your terminal, the most capable way to use Claude for software engineering.
CLAUDE.md
A markdown file at the root of your project that gives Claude project-level instructions, conventions, and constraints.
Claude Hooks
Shell commands Claude Code runs automatically at lifecycle events (before/after a tool call, on session start, on stop) to enforce policies or automate work.
Stack Builder
ClaudeWave's free tool that combines multiple MCP servers into a single claude_desktop_config.json file, ready to paste into Claude Desktop.
Claude Desktop
Anthropic's official Mac and Windows desktop application for using Claude with MCP servers, voice input, artifacts, and persistent chat history.