reject_latest_outfit · Wardrowbe MCP: Risk & Policy

WHAT IT DOES

What reject_latest_outfit does on Wardrowbe

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

WHY IT NEEDS A POLICY

Why reject_latest_outfit needs a policy

This tool modifies data (outfit suggestion state) reversibly—the rejection can be undone by accepting a new suggestion or resubmitting. It does not delete or destroy data permanently, nor does it execute arbitrary code or affect financial/read-only operations. It fits the Write category (creates or modifies data reversibly).

From the tool's definition Tool performs a rejection action on a pending outfit suggestion, reversibly modifying the state of that suggestion without permanent deletion. Description states: 'Reject the most recent pending/sent outfit suggestion.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reject_latest_outfit Rate-limited

reject_latest_outfit 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": {
    "reject_latest_outfit": {
      "limits": [
        {
          "counter": "reject_latest_outfit_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 Wardrowbe, so you can run agents against it safely.

FAQ

Questions about reject_latest_outfit

What does the reject_latest_outfit tool do? +

Reject the most recent pending/sent outfit suggestion. It is categorised as a Write tool in the Wardrowbe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reject_latest_outfit? +

Register the Wardrowbe MCP server in PolicyLayer and add a rule for reject_latest_outfit: 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 Wardrowbe. Nothing to install.

What risk level is reject_latest_outfit? +

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

Can I rate-limit reject_latest_outfit? +

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

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

reject_latest_outfit is provided by the Wardrowbe MCP server (saya6k/mcp-wardrowbe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.