Command Palette

Search for a command to run...

Home / Servers

<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="examples/brand/wordmark-dark.png"> <img src="examples/brand/wordmark-light.png" width="560" alt="A2UI Catalog"> </picture>

The vocabulary layer for A2UI — useful for humans · declarative for agents.
The model names an atom. The renderer compiles the HTML, CSS, SVG, and animation.

<!-- readme-badges:start -->

Atoms Surfaces MCP ARD License A2UI

<!-- readme-badges:end -->

Independent, unofficial catalog — not affiliated with or endorsed by Google. A2UI is Google's protocol; the official spec lives at a2ui.org.

</div>

The idea

Rather than asking an agent to generate custom UI every turn — expensive, fragile, unpredictable — give it a stable vocabulary of atoms and let it compose from those.

Raw HTML   609 tok  ████████████████████████████████████████
OpenUI     287 tok  ███████████████████
A2UI        68 tok  ████

Fewer tokens to describe the same UI. The model names an atom; the renderer expands it into the full HTML server-side, and that expansion never re-enters the model's context window. (The efficiency framing here is still being validated — see benchmarks/BENCHMARK.md for the current methodology.)

Work in progress. The atom vocabulary itself is stable; what it's for is still being explored. The live catalog and this repo are the vocabulary and its renderers — applying that vocabulary to new use cases (rendering a CLI's own output, for instance, in a sibling project not yet published) is ongoing, not finished.


Connect an agent

The catalog is consumable three ways, no signup for any of them — BYO by design: renders happen in your environment, your data never touches us.

ChannelEndpointWhat an agent gets
MCP servera2uicatalog.ai/mcpTools to browse catalogs, validate/compose payloads, emit render URLs, and render live views on MCP Apps hosts
ARD manifest/.well-known/ai-catalog.jsonAgentic Resource Discovery — every atom as a crawlable, typed entry
Machine cataloga2uicatalog.ai/spec.jsonThe full schema in one fetch — types, fields, surface compatibility, degradation notes

5-minute quickstarts: Claude (Desktop / claude.ai) · Gemini Enterprise (BYO-MCP)

As an agent skill — this repo ships a SKILL.md, so any agent using the skills ecosystem can pick up the catalog's when-to-use guidance directly:

npx skills add a2uicatalog/a2ui@a2ui-atomic-catalog

A few atoms, live on the site — click through to a full spec + fields table for each:

<table> <tr> <td align="center"><a href="https://a2uicatalog.ai/atoms/glowing_stat/"><img src="examples/atom-glowing-stat.png" width="240" alt="glowing_stat atom preview"></a><br><a href="https://a2uicatalog.ai/atoms/glowing_stat/"><code>glowing_stat</code></a></td> <td align="center"><a href="https://a2uicatalog.ai/atoms/stat_card/"><img src="examples/atom-stat-card.png" width="240" alt="stat_car

Related servers

n8n

Updated today

by n8n-io

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

NOASSERTION199,059

mcp-server-fetch

OfficialUpdated today

by modelcontextprotocol

A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs

89,138

@modelcontextprotocol/server-filesystem

OfficialUpdated today

by modelcontextprotocol

MCP server for filesystem access

SEE LICENSE IN LICENSE89,138

@modelcontextprotocol/server-everything

OfficialUpdated today

by modelcontextprotocol

MCP server that exercises all the features of the MCP protocol

89,138