MCP (Model Context Protocol) is an open protocol, published by Anthropic in November 2024, that standardizes how an AI application (assistant, agent, code editor) connects to external tools and data sources.
An MCP server exposes three kinds of elements: resources to read, tools to call (actions) and prompt templates. An MCP client, such as Claude, Cursor or VS Code, uses them all in the same way. An integration written once therefore works with several AI applications.
The protocol has been adopted beyond Anthropic, notably by OpenAI and Google. Many vendors publish their own MCP server (GitHub, Notion, Slack, Stripe…) so that agents can act inside their products.
Why it matters when hiring
MCP matters to teams building agents or wanting their product to be usable by agents. A good candidate has already written a server, not just plugged in an existing one, and brings up security unprompted: which actions to expose, with which permissions, how to stop an instruction hidden in data from hijacking the agent.