These are the protocols shaping how AI agents discover services, talk to each other, pay for things, and interact with users. Each Short covers one protocol — what it is, why it exists, and how it works — in under 60 seconds.
🔵 Programmatic Tool Calling#
By Anthropic. How LLMs use tools.
The foundation of agentic AI — how a language model decides to call an external function, what parameters to pass, and how to handle the result. The building block everything else is built on.
🟢 A2A — Agent-to-Agent#
By Google. “HTTP for AI agents.”
Defines how agents discover each other, negotiate capabilities, and delegate tasks. Agents expose an endpoint; other agents call it. No shared memory, no tight coupling.
🟡 UCP — Universal Commerce Protocol#
By Google. Agentic commerce infrastructure.
Merchants publish a .well-known/ucp endpoint. Agents discover it, browse offers, and complete checkout — no human in the loop. Think of it as “Stripe for AI agents,” but a protocol, not a company.
🟣 AG-UI — Agent-to-User Interface#
By CopilotKit. Real-time agent output streaming.
A transport protocol for streaming partial results, tool outputs, and UI state updates from agents to users — without waiting for full task completion. Makes agents feel fast and interactive.
🔵 MCP — Model Context Protocol#
By Anthropic. The “USB-C for AI tools.”
Standardizes how LLMs discover and call tools, access resources, and receive structured prompts. Now the de facto standard — adopted by Google, OpenAI, Cursor, and the broader ecosystem.
🔴 ACP — Agentic Commerce Protocol#
By OpenAI + Stripe. Payment mandates for agents.
Defines how agents request payment authorization from users, store mandates, and trigger recurring or conditional payments — without interrupting the agent’s flow for every transaction.