Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add a2uicatalog/a2ui --skill a2ui-mcpgit clone --depth 1 https://github.com/a2uicatalog/a2uiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/a2uicatalog/a2ui/a2ui-mcp)<a href="https://agentmods.dev/skills/a2uicatalog/a2ui/a2ui-mcp"><img src="https://agentmods.dev/badge/skills/a2uicatalog/a2ui/a2ui-mcp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.01034 |
| Opus 5 | $0.00051 | $0.00517 |
| Sonnet 5 | $0.00021 | $0.00207 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
a2ui-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connecting to the A2UI MCP server
The default: no credential at all
https://a2uicatalog.ai/mcp
Public, unauthenticated, no signup, no API key. POST speaks JSON-RPC 2.0 (MCP
Streamable HTTP): initialize → tools/list → tools/call. GET the same URL with
Accept: application/json for a machine-readable server descriptor (every tool, current
rate limits, docs links) instead of the human landing page.
POST https://a2uicatalog.ai/mcp
Content-Type: application/json
{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}
If a scanner, spec, or setup wizard told you to look for /auth.md, this is the short
answer: just call the endpoint above. The rest of this skill is about the optional
authenticated path most integrations don't need.
A separate documentation server
https://a2uicatalog.ai/mcp-docs is a DIFFERENT MCP identity (a2uicatalog-docs)
exposing search_docs(query) / list_docs() — it answers questions FROM this product's
own docs (auth, versioning, pricing, rate limits). The server above TAKES ACTIONS
(compose, render, publish); this one only answers doc questions. Don't confuse the two
when an agent needs to look something up rather than do something.
Rendering inline: MCP Apps
Hosts that negotiate the io.modelcontextprotocol/ui extension in their initialize
request get inline rendering: render_surface returns a live, interactive view inside
the conversation via a ui:// resource — no URL, no size ceiling, nothing stored. On a
host that doesn't support MCP Apps, the same tool call just returns the payload as text
instead of erroring, so it's always safe to call.
When you actually need a credential
Enterprise platforms whose connector model can't call an unauthenticated service (e.g.
Gemini Enterprise's BYO-MCP data store, which requires OAuth 2.0) use a second, gated
endpoint: https://a2uicatalog.ai/mcp-auth — the SAME tools as /mcp, behind a real
credential. Three accepted mechanisms, in precedence order: Authorization: Bearer <token> (OAuth 2.0 authorization-code flow), X-Api-Key: <key> (for connector
templates that offer an API-key field but no OAuth), Authorization: Basic <base64(user:pass)>. An unauthenticated request to /mcp-auth returns 401 with a
WWW-Authenticate header carrying a resource_metadata pointer to the RFC 9728
protected-resource metadata document.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 81 lines · 103 tokens per session scan A 5591b6065b56
a2ui-mcp is a skill published in the GitHub repository a2uicatalog/a2ui (3 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,034 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.