AI Glossary Term

What does “MCP (Model Context Protocol)” mean?

Definition

An open protocol that lets AI applications connect to external tools, data sources, and context providers in a standard way.

Browse the full AI Glossary Explore all free AI guides

How MCP (Model Context Protocol) works

Example

A coding assistant uses MCP to connect to a project's files and a ticket tracker. Each integration is exposed as an MCP server, so the same assistant can use any compatible tool without custom code for each.

Why it matters

A common protocol reduces one-off integrations. Connected tools also widen what an assistant can access, so permissions matter.

Common questions

Who created MCP?

Anthropic introduced it as an open standard in late 2024, and other vendors have adopted it.

What can an MCP server offer?

Tools the model can call, data resources to read, and prompt templates.

Is it secure by itself?

No. Security depends on what each server exposes and how access is approved.

Algorithmic TransparencyHow clearly an AI system's logic, data sources, and limitations are documented and understandable.Function CallingA model capability to generate structured calls that trigger external tools or APIs.Tool UseA model's ability to call external tools such as search, calculators, or APIs.Machine Learning (ML)Methods that allow systems to learn patterns from data and improve over time.Memory (Agent Memory)Stored context an AI agent uses across steps or sessions to improve continuity.Multimodal ModelA model that can process or generate multiple data types such as text, image, and audio.

Learn more in our free guides

AI Models Explained Model Collapse Model Lifecycle Model Context Protocol

Test yourself

AI Models Explained Quiz Model Collapse Quiz Model Lifecycle Quiz