Infrastructure

Model Context Protocol (MCP)

Also known as: model context protocol

In one line

An open standard from Anthropic that lets any AI app securely connect to any tool or data source.

What does Model Context Protocol (MCP) mean?

MCP defines a universal way for AI assistants to discover and use external tools — like USB-C for AI. Servers expose data or actions; clients (Claude, Cursor, etc.) connect to them.

A real-world example

A single "Google Drive MCP server" that Claude, ChatGPT, and Cursor can all plug into.

Related terms

AI Agent

An AI system that can take actions on your behalf — not just answer questions.

Tool Use (Function Calling)

Letting an AI trigger external tools or APIs — like calling a function in code.

API

A doorway that lets one piece of software talk to another — how apps call AI models.