menami_submit_feedback · Menami MCP: Risk & Policy

WHAT IT DOES

What menami_submit_feedback does on Menami

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

WHY IT NEEDS A POLICY

Why menami_submit_feedback needs a policy

This tool modifies user data (taste profile) reversibly through feedback submission. It is a Write operation—data is created/updated but not destroyed, and the action is undoable (feedback can be corrected or retracted). The blast radius is minimal since feedback only affects personalization logic, not financial transactions, system state, or sensitive operations.

From the tool's definition Tool name 'menami_submit_feedback' and description 'Rate your dining experience. Feedback updates your taste profile' indicate the tool creates or modifies user preference data (taste profile) based on feedback submission.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

menami_submit_feedback Rate-limited

menami_submit_feedback 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": {
    "menami_submit_feedback": {
      "limits": [
        {
          "counter": "menami_submit_feedback_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 Menami, so you can run agents against it safely.

FAQ

Questions about menami_submit_feedback

What does the menami_submit_feedback tool do? +

Rate your dining experience. Feedback updates your taste profile so. It is categorised as a Write tool in the Menami MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on menami_submit_feedback? +

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

What risk level is menami_submit_feedback? +

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

Can I rate-limit menami_submit_feedback? +

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

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

menami_submit_feedback is provided by the Menami MCP server (menami-ai/menami). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.