原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚 登录

A2UI Atomic Catalog

✓ a2uicatalog.ai

作者:a2uicatalog版本 1.0.0i★ 7 (整个仓库的星标)i在云端运行官方网站 ↗
注册名称ai.a2uicatalog/catalog

安装方法

能做什么

500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key.

作者提供的原文

  • 连接方式 在云端运行
  • 账号或密钥 无需密钥
  • 分类 其他

为什么排在这里

此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列

1. 在 Claude 连接器目录中否
2. 团队实测过否
3. 适合泰国用户否
4. 不计星标的使用量20/100热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0
5. 登记日期2026-11-10

用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。

质量: 基础检查通过 4/4 项(仅展示,不用于排序)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 A2UI Atomic Catalog。按照 https://mcp.popnx.com/i/a2uicatalog-catalog.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 4/4 项检查 · 你的提问会经过开发者的服务器(a2uicatalog.ai) · ✓ 命令已检查 2026年11月20日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 2 分钟

不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称A2UI Atomic Catalog
    Remote MCP server URL · 地址https://a2uicatalog.ai/mcp

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsA2UI Atomic Catalog

  4. 试一试

    用 A2UI Atomic Catalog 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 A2UI Atomic Catalog,或回答中出现 A2UI Atomic Catalog 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称A2UI Atomic Catalog
    Connection · 地址https://a2uicatalog.ai/mcp
  3. 在聊天中选择 A2UI Atomic Catalog

    开启新聊天,输入前先从插件列表中选择 A2UI Atomic Catalog

  4. 试一试

    用 A2UI Atomic Catalog 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 A2UI Atomic Catalog,或回答中出现 A2UI Atomic Catalog 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user catalog https://a2uicatalog.ai/mcp
  3. 在 Claude Code 中输入 /mcp

    应能看到 A2UI Atomic Catalog 在列表中并显示已连接

  4. 试一试

    用 A2UI Atomic Catalog 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 A2UI Atomic Catalog,或回答中出现 A2UI Atomic Catalog 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 A2UI Atomic Catalog 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 A2UI Atomic Catalog,或回答中出现 A2UI Atomic Catalog 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 2 分钟

不需要密钥,不用安装程序

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 A2UI Atomic Catalog 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 A2UI Atomic Catalog,或回答中出现 A2UI Atomic Catalog 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://a2uicatalog.ai/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 A2UI Atomic Catalog 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user catalog https://a2uicatalog.ai/mcp

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "catalog": {
      "url": "https://a2uicatalog.ai/mcp"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "catalog": {
      "type": "http",
      "url": "https://a2uicatalog.ai/mcp"
    }
  }
}

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

GitHub 星标i
7 (整个仓库的星标)
该仓库包含多个 MCP 条目,星标在排名中只计算一次
每周下载量i
不在 npm/PyPI 上
已验证域名
✓ a2uicatalog.ai
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.0.0
分类i
其他
发布到注册中心i
2026年11月11日
代码最后更新i
2026年11月19日
最近检查
2026年11月16日
作者
a2uicatalog
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月16日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • list_catalogs

    List every A2UI catalog with a when-to-use, so you can pick the extension catalogs a surface needs. The base catalog (a2ui-atoms-v1) is always resolved.

  • get_catalog

    Return one catalog's atoms (type + one-line description) so you know its vocabulary.

  • find_atoms

    Semantic search over the atom catalog: describe the UI piece you need in plain words and get the best-matching atoms, ranked best-first, each with a description and an example need. YOU choose from the list (the first entries are most likely, but check the descriptions), then cal

  • get_atom_schema

    Return the PROP SHAPE (field names + what each field takes) for named atoms. get_catalog tells you an atom EXISTS; this tells you how to fill it. Call this before authoring any atom you have not used before — guessing prop names is the single most common cause of an atom renderin

  • required_catalogs

    Given an A2UI payload, return the resolvable catalog URIs it needs (deterministic — pure function of the atoms).

  • build_multi_page_surface

    Build a multi-section A2UI app from raw title+content sections — you never estimate size or decide how to split; each section becomes its own independently-encoded page (no shared hub, so per-page size never grows with page count — genuinely unlimited sections). Returns the first

  • make_surface_url

    Render an A2UI payload in the CALLER'S OWN environment. Pass renderer_url (your deployed renderer /exec) and get a live URL + the catalogs it declares. Omit renderer_url to get the encoded fragment + BYO guidance. We host nothing and never see your content. NEVER hand-write your

  • preview_url

    Quick DEMO render on the public renderer (ephemeral, nothing stored). Limited to 2 runs per client, then deploy your own renderer and use make_surface_url. Onboarding only — not the workflow. DATA-IN-URL: keep payloads SMALL (URL < ~2000 chars); large payloads make long URLs that

  • render_surface

    Render an A2UI payload INSIDE the chat as a live interactive view (MCP Apps hosts only — on other hosts this returns the payload as text). No URL, no size ceiling, nothing stored: the payload travels in the tool result and renders in the a2ui_catalog_view. Accepts the blocks dial

  • make_film

    Make a short motion film (a social clip, launch teaser, quote card...) built by the A2UI Design Studio: you choose a template and supply the words; the studio builds the film. Use this instead of composing motion_timeline blocks yourself. It plays inline here and comes with a lin

  • sketch_agent_start

    Start a real, live agent_sketchpad drawing: one Gemini call plans a complete picture as an ordered list of SVG strokes, the first stroke renders immediately, and the rest reveal as you call sketch_agent_poll again — a real multi-turn task, not a single one-shot render. MCP Apps h

  • sketch_agent_poll

    Continue a sketch_agent_start task: returns every stroke newer than the given cursor (an event log, not a snapshot — nothing is skipped regardless of poll timing) plus the next cursor, reveals the result in-chat the same way render_surface does, and reports whether the drawing is

  • render_ping

    Diagnostic: render a tiny test view in-chat (MCP Apps hosts only). Proves view mounting works independent of the full catalog renderer. Echoes back whatever payload you pass.

  • wasm_spike

    Diagnostic (MCP Apps hosts only): mounts a view that instantiates a tiny hand-assembled WebAssembly module, computes per-frame state in it, renders to canvas, and captures arrow-key input -- the same three ingredients a WASM game port would need. Answers whether THIS host permits

  • diagram_studio

    Draw a diagram in-chat with the full Diagram Studio interface (MCP Apps hosts only; it opens fullscreen where the host allows it). YOU write the diagram; nothing is generated server-side and nothing is stored. PREFER `graph`: give vertices (id, label, type start|process|decision|

  • amiga

    Open a real, cycle-exact Amiga 500 emulator in-chat (MCP Apps hosts only). Boots straight into AROS, a free open-source environment (no copyrighted Kickstart ROM involved), with a public-domain Amiga game already loaded and running. This is a fixed, self-contained retro-computing

  • distill_document

    Compile a training.md / roadmap markdown document into a live interactive A2UI app — DETERMINISTIC parser, no model involved. Fact sheet: input is MARKDOWN following the training-md contract (frontmatter id/domain/name/source/license + a # Steps section); the text transits to the

  • publish_url

    STORES the payload server-side and returns a SHORT shareable link. Opt-in only: requires acknowledge_storage=true — confirm with the user first that they accept operator-hosted storage (ONE WEEK retention on the public tier, revocable earlier via the returned delete_token; anyone

  • unpublish_url

    Delete a published short link before its TTL using the delete_token returned by publish_url.

  • emit_deployment

    🎓 GRADUATE a tested surface into a dedicated, DEPLOYER-ONLY standing app in YOUR OWN Google Apps Script account. Returns a deterministic recipe (config files + clasp ops + least-privilege scopes derived from the atoms + verify) — you run it with your own clasp; nothing runs on o

  • emit_training_runbook

    Build a multi-lesson training/course surface as ONE properly-linked page with real in-app tab navigation between lessons — prefer this over build_multi_page_surface for training/course content specifically: that tool produces N independent pages with NO links between them (you mu

  • emit_runbook_surface

    Stamp your content through a DECLARED runbook — a pre-authored, judgment-free surface composition. You supply content only; the runbook supplies the composition (which atoms, how arranged, navigation). DISCOVERY: call with runbook_id only (no content) to get that runbook's input_

  • describe_playbook

    Explain a playbook to a HUMAN as a rendered surface: the frame it reads against, the lenses available, and the questions it will ask them. Compiled from the runbook declaration, so it costs nothing and cannot drift from what the stamper enforces. This is NOT emit_runbook_surface

  • open_workspace

    Open the A2UI Workspace — a rendered surface that IS the demo: each tool is introduced by the scenario it answers, then wired to run, then shows what it saved. This tool RENDERS ITSELF: its result carries the view, so call it alone and show the result — do NOT pass it on to rende

  • get_profile

    Read the signed-in reader's saved profile and recent history. Call this BEFORE asking a runbook's `elicit` questions: if a domain or default lens is already saved, CONFIRM it ("reading as: a2ui, generative ui — change?") instead of asking from scratch. Returns available:false on

  • save_profile

    Update the signed-in reader's profile. Only the keys you pass change; pass null to clear one. Save what the reader TOLD you, never what you inferred from one article — a profile that drifts on every reading is worse than no profile, because they stop being able to predict what it

  • save_reading

    Record a stamped surface in the reader's history so it can be compared and reopened later. Call it AFTER emit_runbook_surface, and PASS ITS `payload` — that stores the reading itself rather than a link to it. Silently no-ops when nobody is signed in.

  • export_reading

    Export a kept reading as something that outlives this connector. format "html" returns ONE self-contained file — styles inlined, no network, opens in any browser years from now with nothing installed. "url" rebuilds a link against any renderer (yours by preference). "surface" ret

  • render_reading_to_slack

    Post a kept reading into Slack as real, native Block Kit — the continuity proof: generate here, save it, and the SAME content reopens in Slack, not a link back to a renderer. Requires the caller's Slack account to already be linked (`/a2ui link` in Slack) and only works on an aut

  • list_readings

    The reader's recent stamped surfaces, newest first — what makes "compare this to my last three teardowns" answerable at all. Optionally filter to one runbook. Returns available:false when nobody is signed in.

  • delete_reading

    Permanently remove one or more of the reader's saved readings from their History. Takes an array so the Workspace's multi-select can delete a batch in one call rather than one round trip per row. Ids that don't exist (or belong to someone else's history) are silently skipped — th

  • read_article

    Have the catalog's own model (Gemini) read an article through the article_playbook runbook and KEEP the reading in the signed-in reader's history, in one call. For a client with no model of its own (the Android analyser app), or when the reader asks for a Gemini reading. If you c

  • deck_schema

    List the slide layouts the PPTX renderer builds (title, bullets, stats, quote, table, media, cta), each field with its limits, the targets, the film-only scenes, and the A2UI atoms that have a slide recipe (payload_atoms). Read this before writing a deck.

  • deck_validate

    Check a deck (scene list or A2UI payload) without building it. Returns every error with its slide, field and exact limit, warnings (no speaker notes, no link) and, for a payload, which atoms have no slide recipe. Not rate-limited.

  • deck_build

    Build a PowerPoint (.pptx) file from a scene list or an A2UI payload. Deterministic (same input, same bytes), nothing is stored or fetched, text is fitted with real font metrics and the file is linted (overlap, bounds, contrast, alt text). Returns the file as an embedded resource

  • drawio_open

    Open a diagram you wrote in draw.io (diagrams.net). YOU write the diagram as mxGraph XML, the format draw.io reads; this tool checks it, and returns a link that opens it in the draw.io editor for the person, plus a .drawio file to download (kept for one hour). Nothing is drawn or

  • unlink_slack_account

    Revoke one or more Slack accounts' link to this reader's store, from the Workspace side (the reverse of the Slack-side `/a2ui unlink` command — see slack-compiler/DESIGN-identity.md, "many Slack -> one sub"). Removes that account's ability to post via render_reading_to_slack or r

  • wall_calc

    Compute a coursed block/brick wall specification — course and unit counts, weight, cost, mortar bags, a build-time curve across 1-6 builders, and load-bearing/height advisories. Pure arithmetic, no model call: a native-catalogue rebuild of the Gemini Enterprise "Wall Builder" dem

  • whoami

    Report who this connection is authenticated as. Answers two SEPARATE questions that are easy to conflate: which APPLICATION is connected (the OAuth client), and which HUMAN authorised it (the signed-in account, when the endpoint is one that can know). The public endpoint is anony

  • identify_model

    CALL THIS FIRST, before any other a2ui-catalog tool, once per session. Declares your own model identity so this response can hand you capability-matched guidance up front — some models need simpler, judgment-free tools; skipping this just means you default to the full toolkit, in

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 a2uicatalog.ai 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于昨天

  • – 不适用

    有许可证

    不适用:由 a2uicatalog.ai 的所有者自己运行的云端服务器,你不会运行仓库里的代码

  • ✓ 通过

    端点有响应

    在 235 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 40 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/a2uicatalog-catalog.svg)](https://mcp.popnx.com/en/servers/a2uicatalog-catalog)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20868 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 20868 个服务器的 84% 更新
  • 基础检查结果等于或优于此分类中其他 20868 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

A2UI Atomic Catalog 安全吗?

它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于昨天,最新版本(1.0.0)于9天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万4天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92762个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582414个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
A2UI Atomic Catalog
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
运行位置在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查4/44/44/44/41/44/4
许可证MITAGPL-3.0AGPL-3.0MITApache-2.0MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

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.

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


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.

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 — so the tokens spent *describing* a UI are a fraction of the tokens in the rendered result.

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/ard.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:

glowing_stat

stat_card

before_after

annotated_code

Browse all 573 atoms →


Google Apps Script renderer — try it live

Most of the catalog's atoms run natively in Google Apps Script (the live count is on /renderer/). No CDN, no dependencies, no server. Paste a JSON block list, get a rendered page.

Protocol support: A2UI v1.0 createSurface messages, with all 18 Basic Catalog components, data-model bindings and button actions. v0.9 and v0.8 input is refused. Details and a minimal v1.0 example: a2uicatalog.ai/renderer/#protocol.

{

"title": "Hello A2UI", "theme": "light", "blocks": [ { "type": "heading", "level": 1, "text": "My first A2UI page" }, { "type": "callout", "icon": "💡", "text": "Built with A2UI atoms in Google Apps Script." }, { "type": "chartjs_bar", "title": "Quick chart", "bar_color": "#6366f1", "data": [{ "label": "A", "value": 80 }, { "label": "B", "value": 45 }, { "label": "C", "value": 62 }] } ] }

What's in the GAS renderer
FeatureDetail
Most of the catalogApps Script surface — superset of the web article renderer (live count)
CSS-only interactionsTabs, carousel, gallery lightbox, modals, accordions — zero JS required
Inline SVG chartsBar, line, pie, donut, heatmap, punch card, sankey, cohort retention, GitHub activity grid
8 form input typestext, email, select, radio, checkbox, switch, slider, date — native HTML controls
Animation fallbacks32 motion atoms degrade to readable content cards
No CDNWorks inside GAS sandboxed iframes with no external requests
Large payload supportAutomatically switches to POST for schemas too large for a URL
Deploy your own renderer (recommended)

The renderer is fully open source. Deploy your own instance — you own the URL, you own the deployment, no dependency on the catalog's demo endpoint.

git clone https://github.com/a2uicatalog/a2ui

cd a2ui/apps-script-surface/gas-wired-renderer clasp login clasp create --type webapp --title "My A2UI Renderer" clasp push clasp deploy

→ Your renderer is live at https://script.google.com/macros/s/YOUR_ID/exec

Call it with any payload from the catalog (illustrative — encode() stands in for gzip + base64url of the JSON, see scripts/make_url.py for the exact encoding):

function doGet() {

const blocks = [ { type: "stat_card", value: "1,234", label: "Daily users", delta: "+12%", is_up: true }, { type: "progress_bar", value: 75, label: "Q2 target" } ]; const url = "https://script.google.com/macros/s/YOUR_ID/exec"; return HtmlService.createHtmlOutput( ); }

The catalog's "Try it live" button uses a shared demo instance of the same renderer. For anything beyond exploration, deploy your own.


What's in this repo

DirectoryContents
atoms/Atom schema definitions (schema.yaml)
renderers/Surface renderers — web_article.py is the canonical web renderer
apps-script-surface/GAS renderer — atom.gs + atom files (no CDN); gas-wired-renderer/ is the current one, A2UI v1.0
components/Lit Web Components for the meet-stage surface
scripts/Build pipeline — atom pages, spec.json, MCP bundle, README compat matrix, link/brand checks
vendors/Landscape analysis of 9 UI libraries mapped to A2UI atoms
benchmarks/Token comparison study (BENCHMARK.md)
spec/Internal state/action contracts (gdm-v0.2, a2ui-state-v1) — the A2UI v1.0 candidate spec itself lives at a2ui.org, not vendored here
examples/Playbook YAML examples
knowledge-catalogue/Curriculum-to-atom pipeline — schema-validated curriculum markdown (Brevet 2026, NIST AI RMF) compiled into A2UI payloads. Separate concern from the atom vocabulary itself.

573 atoms across 13 surfaces

Atoms declare which surfaces they support at the schema level. An agent picks an atom by name, supplies parameters, and the renderer handles the rest.

[{

"type": "stat_card", "label": "Daily users", "value": "1,234", "delta": "+12%" }]

Agents never write HTML. They compose from the vocabulary.


Surface compatibility

Every atom declares, at the schema level, which of the 13 surfaces it works on and where it degrades (with a note explaining the caveat). The matrix below is generated straight from public/spec.json — the same file agents consume — so this README can no longer drift from the catalog.

View full compatibility matrix (all atoms × 13 surfaces)

573 atoms · generated from public/spec.json by scripts/gen_compat_matrix.py — do not edit by hand.

Atomwebgas-webgas-panelmeetchatchat-chromiummcp-appsclaude-codeandroidemailpdfslidespptxSource · license
abbr_tooltip✅✅—⚠️——✅—✅⚠️———a2uicatalog · MIT
accordion_item✅✅—✅——✅—✅————a2uicatalog · MIT
achievement_badge✅✅—✅⚠️—✅—✅✅✅——a2uicatalog · MIT
action_items✅✅————✅—✅—✅✅✅a2uicatalog · MIT
action_required_card✅✅—✅✅—✅—✅⚠️———a2uicatalog · MIT
actual_vs_estimate✅✅————✅—✅⚠️———a2uicatalog · MIT
adsb_feed—✅———————————a2uicatalog · MIT
agenda_block✅✅————✅—✅————a2uicatalog · MIT
agent_sketchpad✅✅—✅⚠️—✅—✅—⚠️——a2uicatalog · MIT
ai_build_trace—✅————✅—✅————a2uicatalog · MIT
airspace_command_deck—✅—✅——✅—✅————a2uicatalog · MIT
alert_banner✅✅—✅⚠️—✅—✅————UIverse.io community · MIT
ambient_gradient⚠️✅————✅—✅————a2uicatalog · MIT
anchor_list✅✅—✅⚠️—✅—✅✅✅✅✅a2uicatalog · MIT
animated_beam✅✅⚠️✅⚠️—✅—✅—⚠️——a2uicatalog · MIT
animated_border✅✅✅✅——✅—✅————a2uicatalog · MIT

| animated_border_card | ✅ | ✅ | — | ✅ | ⚠️ | — | ✅ | — | ✅ | — | ⚠️ | — | — | [a2u

只显示了开头部分;其余内容请在仓库中阅读