Skip to main content

Tools and extensions

How a model does something rather than only saying something. The tool-call loop, and the three ways a harness is extended: skills, plugins, and MCP servers.

📄️MCP in depth

The Model Context Protocol (MCP) is an open standard designed to decouple AI applications from the external tools, data sources, and services they interact with. Rather than building bespoke integrations between every tool and every assistant, MCP establishes a client-server architecture: servers publish their capabilities, clients connect to discover and invoke them, and neither side needs bespoke knowledge of the other. This guide examines how the protocol works, its architectural roles and network transports, session initialization mechanics, authentication patterns, and real-world operational costs.