docs/snippets/shared/generative-ui-specs-overview.mdx
import Image from "next/image"
<Image src="/images/gen-ui-specs-light.png" alt="Generative UI Specs" width={4096} height={2304} className="block dark:hidden mb-8" /> <Image src="/images/gen-ui-specs-dark.png" alt="Generative UI Specs" width={4096} height={2304} className="hidden dark:block mb-8" />
Several recently released specifications enable agents to return generative UI, increasing the power and flexibility of the Agent-to-User conversation.
A2UI, MCP Apps, and Open-JSON-UI are all generative UI specifications that allow agents to respond to users not only with text but also with dynamic UI components. CopilotKit now provides universal support for all major Generative UI specifications.
| Specification | Origin / Maintainer | Purpose |
|---|---|---|
| A2UI | A declarative, LLM-friendly Generative UI spec. JSONL-based and streaming, designed for platform-agnostic rendering. | |
| Open-JSON-UI | OpenAI | An open standardization of OpenAI's internal declarative Generative UI schema. |
| MCP Apps | MCP Ecosystem | Iframe-based Generative UI extending MCP, enabling servers to return interactive UI components. |
Despite the naming similarities, AG-UI is not a generative UI specification — it's a User Interaction protocol that provides the bi-directional runtime connection between the agent and the application.
AG-UI natively supports all of the above generative UI specs and allows developers to define their own custom generative UI standards as well.
Explore each specification in detail:
Or learn about related protocols: