brand_import · RC Engine MCP: Risk & Policy

WHAT IT DOES

What brand_import does on RC Engine

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

WHY IT NEEDS A POLICY

Why brand_import needs a policy

brand_import reads brand assets and configuration files as input, then writes structured output (BrandProfile JSON) that persists in the project directory and affects downstream tool behavior. This is Write rather than Read because it creates new normalized data artifacts. It is not Execute because it does not run arbitrary code or trigger external operations based on user input.

From the tool's definition Tool creates and saves a normalized BrandProfile to rc-method/design/BRAND-PROFILE.json, which is a persistent data artifact.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

brand_import Rate-limited

brand_import 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": {
    "brand_import": {
      "limits": [
        {
          "counter": "brand_import_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches RC Engine, so you can run agents against it safely.

FAQ

Questions about brand_import

What does the brand_import tool do? +

Import brand assets during Phase 1 (Illuminate). Auto-detects colors, fonts, and design tokens from project files (tailwind config, CSS variables, constants/). Optionally scrapes a URL for brand signals. Produces a normalized BrandProfile saved to rc-method/design/BRAND-PROFILE.json. The profile is consumed by design_research_brief, ux_design, and copy_generate for brand consistency. It is categorised as a Write tool in the RC Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on brand_import? +

Register the RC Engine MCP server in PolicyLayer and add a rule for brand_import: 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 RC Engine. Nothing to install.

What risk level is brand_import? +

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

Can I rate-limit brand_import? +

Yes. Add a rate_limit block to the brand_import 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 brand_import completely? +

Set action: deny in the PolicyLayer policy for brand_import. 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 brand_import? +

brand_import is provided by the RC Engine MCP server (originalrashmi/rc-engine-product-framework). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.