SHRIKEModel Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard that lets AI applications connect to external tools and data sources in a uniform way. A client (the agent host) discovers what an MCP server offers, then calls those tools during a task. MCP is to agent tooling what USB was to peripherals: one connector, many capabilities.
Before MCP, every agent-to-tool integration was bespoke. After it, servers publish tools with names, descriptions, and JSON schemas, and any compliant client can use them. That composability is the point, and the security catch: the protocol standardizes capability, not trust. Anything an agent connects to can describe tools, and descriptions are read as trusted context. The threat side is covered under MCP security.
Related
Shrike governs AI agent actions in real time: every command, query, and tool call evaluated against policy before it executes. Start with what is action governance or the quickstart.