Launching soon — get early access:
Back to Glossary
Technical

Model Context Protocol(MCP)

Definition

An open standard, introduced by Anthropic, that lets AI applications connect to external data sources and tools through a uniform interface.

In-Depth Explanation

MCP is often described as "a USB-C port for AI" — a single protocol so any compliant AI app can talk to any compliant data source or tool without bespoke integrations. It defines two inverse roles: MCP servers expose data, tools, and prompts, while MCP clients (hosts like Claude Desktop, Cursor, or VS Code) consume them. Introduced by Anthropic in late 2024, it is now supported across many AI assistants and developer tools. It reduces the N-by-M integration problem to one shared interface.

Real-World Example

Connecting Claude to a filesystem or GitHub MCP server lets it read local files and repositories directly during a conversation.

3 views0 found helpful

Related Terms

AI Agent

An autonomous AI system that can perceive its environment, make decisions, and take actions to achieve specific goals.

Function Calling

An LLM capability where the model outputs structured JSON matching a predefined schema so an application can invoke external functions or APIs.

MCP Server

A program that exposes data, tools, or prompts to AI applications over the Model Context Protocol, acting as the provider side of MCP.

Tool Use

The capability of AI models to interact with external tools, APIs, and systems to accomplish tasks.