rh11_feedback_submit · Rhodium11 MCP: Risk & Policy

WHAT IT DOES

What rh11_feedback_submit does on Rhodium11

AI agents use rh11_feedback_submit to create or update resources in Rhodium11 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rhodium11 environment.

WHY IT NEEDS A POLICY

Why rh11_feedback_submit needs a policy

This tool creates new feedback entries in the system, which is a reversible write operation. The severity is low because feedback submission has minimal blast radius—it cannot delete data, trigger financial transactions, or execute arbitrary code. An AI agent misusing this tool could at worst spam feedback, but the duplicate rejection mechanism provides some protection.

From the tool's definition Tool submits feedback (writes data) with character limit 10-5000 characters. Description indicates creation of new feedback records without data deletion or financial impact.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rh11_feedback_submit Rate-limited

rh11_feedback_submit 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": {
    "rh11_feedback_submit": {
      "limits": [
        {
          "counter": "rh11_feedback_submit_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 Rhodium11, so you can run agents against it safely.

FAQ

Questions about rh11_feedback_submit

What does the rh11_feedback_submit tool do? +

Submit feedback to Rhodium11 (10-5000 characters). Do not submit duplicate feedback — identical text will be rejected. It is categorised as a Write tool in the Rhodium11 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on rh11_feedback_submit? +

Register the Rhodium11 MCP server in PolicyLayer and add a rule for rh11_feedback_submit: 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 Rhodium11. Nothing to install.

What risk level is rh11_feedback_submit? +

rh11_feedback_submit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit rh11_feedback_submit? +

Yes. Add a rate_limit block to the rh11_feedback_submit 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 rh11_feedback_submit completely? +

Set action: deny in the PolicyLayer policy for rh11_feedback_submit. 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 rh11_feedback_submit? +

rh11_feedback_submit is provided by the Rhodium11 MCP server (rhodium11/rhodium11-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.