Intermediate · Systems

Model Context Protocol (MCP)

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. An open standard from Anthropic that lets LLM apps connect to external tools, data sources, and prompts through a uniform client–server interface.

Technical Definition

An open standard from Anthropic that lets LLM apps connect to external tools, data sources, and prompts through a uniform client–server interface.

How it works

MCP standardizes how AI assistants discover and call external capabilities. An MCP server exposes resources (files, DBs), tools (functions), and prompts; an MCP client (Claude Desktop, Cursor, etc.) connects over stdio or HTTP and lets the model use them. It decouples model providers from integrations the way LSP decoupled editors from language tooling, and is becoming the de-facto plug-in layer for agentic apps.

Related Concepts

• AI Agent — An AI system that autonomously plans, uses tools, and takes actions to accomplish goals through iterative reasoning.
• Function Calling — Provider-defined schemas that let an LLM invoke developer-supplied functions in a structured way.
• Agentic AI — AI systems designed to independently plan, execute, and adapt actions to achieve a given goal, often involving multiple steps and external tools.
• Tool Use — The ability of an AI model, especially an LLM agent, to autonomously identify, select, and utilize external tools and APIs to accomplish tasks.