Our review
A2UI Atomic Catalog lets AI agents render real interactive UI components — charts, gauges, steppers, dashboards, decision trees — via an MCP server, instead of generating raw HTML.
Strengths
- Fixed vocabulary of 474 typed atoms prevents HTML hallucinations.
- No-auth MCP server, free and open source.
- Supports both inline rendering and shareable preview links.
- Strict JSON schemas per atom avoid invalid field guesses.
Limitations
- Only renders data; it does not fetch arbitrary live data.
- Requires a host that can display HTML or open a link.
- Full catalog is large; must load only the relevant slice for context efficiency.
When the user needs to see interactive data visualizations or UI components and the agent is running on an MCP-capable host that can render visuals or open links.
When a plain text answer is preferable, or when the host cannot display HTML or open links.
Security analysis
CautionThe skill does not include destructive or exfiltrating commands, but it instructs the agent to interact with an external network service for rendering UI, which falls under legitimate network tool usage. No shell commands or secret exfiltration are present, but the external dependency warrants caution.
- •Directs the agent to connect to an external MCP server (https://a2uicatalog.ai/mcp) over the network without authentication, which could expose data or enable remote tool execution if the server is compromised.
Examples
Use the A2UI Atomic Catalog to render an interactive dashboard with a gauge and a line chart showing these quarterly sales numbers: Q1 120k, Q2 145k, Q3 132k, Q4 168k.Using the A2UI catalog, show a decision tree for troubleshooting API error codes 400, 401, 403, 429, and 5xx.Render a stepper UI for a 3-step onboarding flow (Create account → Connect workspace → Invite teammates) with the A2UI Atomic Catalog.name: a2ui-atomic-catalog description: Renders real interactive UI — charts, gauges, steppers, dashboards, decision trees — for AI agents instead of generating raw HTML. Use this skill when a user needs to SEE something rather than read a description of it, and the host (Claude, another MCP client, a Gemini Enterprise agent) can display rendered visuals or open a link. Do not use for plain prose answers, for data retrieval (this renders data, it does not fetch it beyond a few declared sources), or on hosts that cannot display HTML.
A2UI Atomic Catalog
474 typed UI atoms an AI agent composes into real rendered interfaces — web, Google Meet, Apps Script, Google Chat and MCP Apps — instead of writing HTML by hand. The agent names a component from a fixed vocabulary; a renderer that already knows that component draws it.
Connect
MCP server, no auth, no signup, no API key:
https://a2uicatalog.ai/mcp
POST speaks JSON-RPC 2.0 (MCP Streamable HTTP). GET with Accept: application/json
returns a machine-readable descriptor listing every tool, current rate limits, and
documentation links.
How to use it
list_catalogs— pick the catalog slice the task actually needs. Do not load the whole 474-atom vocabulary into context for a one-chart request.get_catalog— read the real field contracts for that slice. Never guess a field name; a hallucinated field is a validation error, not a broken render.- Render, by host capability:
render_surface— MCP Apps-capable hosts (Claude.ai and others): renders inline in the conversation, no URL.preview_url— any other host: returns a shareable link (rate-limited demo renderer).make_surface_url— render against the caller's own deployed renderer instead of the shared demo one; no rate limit.
When this is the wrong tool
- The answer is better as prose than a visual.
- The host cannot display HTML or open a link.
- The task needs live data this catalog doesn't already declare a source for — this skill renders data, it does not fetch arbitrary data.
Reference
| Document | URL | |---|---| | OpenAPI specification | https://a2uicatalog.ai/openapi.json | | Full atom vocabulary | https://a2uicatalog.ai/spec.json | | Strict per-atom JSON Schema | https://a2uicatalog.ai/catalogue/atoms-json-schema.json | | Agent overview | https://a2uicatalog.ai/llms.txt | | A2A agent card | https://a2uicatalog.ai/.well-known/agent-card.json |
Free, MIT licensed, no signup. Independent, unofficial project — not affiliated with, endorsed by, or sponsored by Google or Anthropic. A2UI is Google's protocol; MCP is Anthropic's. Source: https://github.com/a2uicatalog/a2ui
Next.js App Router Expert
Development
A skill that turns Claude into a Next.js App Router expert.
README Generator
Development
Creates professional and comprehensive README.md files for your projects.
API Documentation Writer
Development
Generates comprehensive API documentation in OpenAPI/Swagger format.