New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

create_pack

Create a new PRIVATE design pack in the user's "version library" — YOU (the AI) design it, then pass the HTML + CSS. The server sanitizes (never executes) and stores it, returning { packId, status:"ready", previewUrl } immediately (no polling). previewUrl = demo-<packId>.a3plus.sogdia.market. Pic...

SERVERA3plus SOURCEa3plus-mcp
Medium RISK CLASS
Category Write
Parameters 63 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/a3plus-mcp/create-pack.md

What create_pack does on A3plus

AI agents use create_pack to create or update resources in A3plus, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A3plus environment.

ParameterTypeRequiredDescription
css string All CSS for the page (supports @keyframes/animation/transition for motion).
html string Yes The home-page inner HTML you generated (inside <main>), following the DESIGN RULES above (data-field markers, one <h1>, no scripts).
name string Yes Human name for the pack, ≤120 chars (also becomes the URL slug).
brief string Optional. If you pass a brief INSTEAD of html, the server generates the design itself (async → poll get_pack). Prefer generating the html yourself.
tokens object Optional design tokens metadata (e.g. { colors, font, radius }).
category string Yes A category id from list_pack_categories (e.g. casino, blog, restaurant).

Parameters from the server's own tool schema.

Why create_pack is rated Medium

An AI agent can call create_pack faster than any human can review: one bad instruction and it creates or modifies resources in A3plus by the hundred, each call as confident as the last.

Risk signalsAccepts raw HTML/template content (html)

Questions about create_pack

What does the create_pack tool do? +

Create a new PRIVATE design pack in the user's "version library" — YOU (the AI) design it, then pass the HTML + CSS. The server sanitizes (never executes) and stores it, returning { packId, status:"ready", previewUrl } immediately (no polling). previewUrl = demo-<packId>.a3plus.sogdia.market. Pick category from list_pack_categories. DESIGN RULES for the html you generate: • html = the INNER content of <main> for the home page only. Do NOT include <html>/<head>/<body>/<script>/<style>/<link>. Put ALL CSS in the css field. • Mark injectable per-site content so one design serves many sites: text → data-field="<path>" e.g. <h1 data-field="page.home.hero.headline">Big headline</h1> image attrs → data-field-attr="src:<path>, alt:<path>" e.g. <img data-field-attr="src:page.home.hero.image, alt:page.home.hero.headline"> repeating list → data-loop="articles" on a container; children use relative .title .url .image .category Useful paths: brand.name, brand.ctaText, brand.ctaUrl, page.home.hero.headline, page.home.hero.subhead, page.home.hero.image. • Keep sensible DEFAULT placeholder copy inside the tags so it renders standalone. • EXACTLY ONE <h1>. Semantic HTML (header/sections/footer). Every <img> has alt. Use class names, not inline styles. • Motion is allowed via CSS ONLY: @keyframes / animation / transition / transform in the css field. NO <script>, NO on* handlers, NO external fonts/CDN (use a system font stack). Scripts are stripped and blocked by CSP. It is categorised as a Write tool in the A3plus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_pack accept? +

create_pack accepts 6 parameters: css, html, name, brief, tokens, category. Required: html, name, category. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_pack? +

Register the A3plus MCP server in PolicyLayer and add a rule for create_pack: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches A3plus. Nothing to install.

What risk level is create_pack? +

create_pack is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_pack? +

Yes. Add a rate_limit block to the create_pack rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_pack completely? +

Set action: deny in the PolicyLayer policy for create_pack. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_pack? +

create_pack is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on A3plus, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of A3plus's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.