Model Context Protocol (MCP)
A shared standard for connecting AI models to the tools, data, and systems they need to do work, so each connection does not have to be built from scratch. You can think of it as a common plug that lets a model and an outside system talk to each other. The term is appearing more in agentic AI conversations because it is becoming a common way to wire models into real software. For decision-makers the relevant point is governance: a standard connection still needs the same scrutiny over what data flows through it and what the model is permitted to do once connected.
IT is asked to approve an MCP server that connects an AI assistant to the scheduling system, so staff can ask it to find and book appointments. As installed, the server also exposes patient contact details and the ability to cancel appointments, and any assistant connected to it can reach all of that. Review each server's list of tools and data before connecting it, switch off whatever the use case does not need, and confirm that every action is logged under the staff member who made the request.
Terms like this come up in real clinical scenarios across the HelloAI courses: bite-sized modules with verifiable certificates. An account takes one minute, no password needed.
Sign in →