Agent protocols

Model Context Protocol (MCP)

An open protocol for connecting AI applications to external tools and data through servers that expose them.

The Model Context Protocol is an open protocol that standardises how applications built on language models connect to external data sources and tools. It uses JSON-RPC messages between hosts, which are the AI applications, clients inside them, and servers that expose resources, prompts and tools. Versions of the specification are named by release date, and its security principles require explicit user consent before data is shared or any tool is invoked.

Agent Minute explains this term on 10 October 2026.

Related terms