Mcp

Explains function calling (tool use) in LLMs: how models emit structured requests to invoke external functions, the request-execute-return loop, provider support, and practical reliability notes.

MCP vs plugins: layered distinction (external systems vs assistant-extension packaging); both cross-surface across Claude Code, Cowork, and the Claude apps

Deep-dive into the Model Context Protocol interaction model covering components, OAuth 2.1 authorization, initialization, capability discovery, tool calling, sampling, and elicitation.