MCP & Tooling
Model Context Protocol
Also: MCP
An open protocol that lets AI applications connect to external tools and data sources through a standard interface.
In more detail
Instead of building a custom integration for every tool, an application speaks MCP to servers that expose tools, resources and prompts. That makes agents far more useful and widens the attack surface at the same time: every server you connect can supply text the model trusts and actions the agent can take. Security review of MCP means looking at what each server can do, what it returns, how it authenticates and whether it can change after you approve it.