refine_pack

SERVERA3plus SOURCEa3plus-mcp

Medium RISK CLASS

Category Write

Parameters 51 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

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

WHAT IT DOES

What refine_pack does on A3plus

AI agents use refine_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.

Parameter	Type	Required	Description
`css`	string	—	The full updated CSS (supports @keyframes/animation for motion).
`html`	string	—	The FULL updated home-page inner HTML after your edit (following the create_pack DESIGN RULES).
`packId`	string	Yes	The id of a pack you own (from create_pack / list_packs owner=mine).
`tokens`	object	—	Optional updated design tokens.
`instruction`	string	—	Optional server-side alternative: a single change (3–2000 chars) for the SERVER to apply, instead of passing html. e.g. "make the background dark navy".

Parameters from the server's own tool schema.

RISK

Why refine_pack is rated Medium

An AI agent can call refine_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)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs refine_pack safely

PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For refine_pack, this is the rule to start with:

refine_pack Rate-limited

refine_pack stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "refine_pack": {
      "limits": [
        {
          "counter": "refine_pack_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every refine_pack call is checked against it from then on.

FAQ

Questions about refine_pack

What does the refine_pack tool do? +

Refine a pack you OWN, in place — YOU edit the design and pass the full updated html (+ css). First call get_pack to fetch the current template.home / template.css, apply your change (fix layout, add a section, tweak copy, add CSS motion), then pass the FULL updated html here. Same DESIGN RULES as create_pack (keep data-field markers, EXACTLY one <h1>, no scripts — CSS-only motion). Same packId + previewUrl; the thumbnail refreshes automatically. Runs synchronously and returns when applied. Built-in/official packs cannot be edited (clone with create_pack). Alternatively pass instruction instead of html to have the SERVER apply the change — but prefer editing the html yourself. 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 refine_pack accept? +

refine_pack accepts 5 parameters: css, html, packId, tokens, instruction. Required: packId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on refine_pack? +

Register the A3plus MCP server in PolicyLayer and add a rule for refine_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 refine_pack? +

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

Can I rate-limit refine_pack? +

Yes. Add a rate_limit block to the refine_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 refine_pack completely? +

Set action: deny in the PolicyLayer policy for refine_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 refine_pack? +

refine_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.

KEEP EXPLORING

More on A3plus, and thousands of servers like it.

This server

All 61 A3plus tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →