The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Before MCP, connecting N assistants to M tools meant N times M custom integrations. MCP (introduced by Anthropic in late 2024, since adopted broadly) standardizes the plug: a service exposes an "MCP server" describing its tools, and any MCP-capable assistant can discover and call them.
It's the USB moment for agent tooling — write one server for your database or API and every assistant can use it. The flip side: a standard port for capabilities is also a standard port for risk, so which servers you trust becomes part of your security model.