Model Context Protocol (MCP): a plain-English definition
2026-11-10
Definition
The Model Context Protocol, or MCP, is an open standard (see the Model Context Protocol site) that gives AI assistants a common way to connect to outside tools and data sources such as files, calendars, databases and business apps.
Why it exists
Before a shared standard, every AI product needed its own custom connection to every app. MCP defines one format, so a tool built once as an MCP server can work with every assistant that supports it. It is similar in spirit to an API, but designed for AI models that choose which tool to call and when. This is a key building block for an AI agent.
An assistant connected to your email or files can read what that connection allows, so start with an account that has a clear job, like a shared inbox or one project folder, and set rules through AI governance. Support varies by assistant. The answer on whether the Privacy Act applies to AI tools is a good companion.
A hypothetical example
Imagine a financial planning firm that connects an AI assistant to its client file store through MCP. A planner asks for the last three meeting notes for one client. The assistant fetches those files, and the MCP server's configuration decides which folders it can reach at all.
We design and build connected assistants under AI agents.
