trw_submit_feedback · Trw MCP: Risk & Policy

WHAT IT DOES

What trw_submit_feedback does on Trw

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

WHY IT NEEDS A POLICY

Why trw_submit_feedback needs a policy

The 'submit' verb strongly suggests the tool creates or posts feedback records to persistent storage (consistent with the server's engineering memory goal), making it a Write action. This could reversibly modify stored feedback or learnings. Without a description, severity is estimated as medium—the tool likely affects engineering memory rather than critical systems, and feedback submission is generally reversible.

From the tool's definition Tool name 'trw_submit_feedback' contains 'submit', which indicates creation or modification of feedback data. The description is empty, limiting confidence in exact behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trw_submit_feedback Rate-limited

trw_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": {
    "trw_submit_feedback": {
      "limits": [
        {
          "counter": "trw_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 Trw, so you can run agents against it safely.

FAQ

Questions about trw_submit_feedback

What does the trw_submit_feedback tool do? +

trw_submit_feedback. It is categorised as a Write tool in the Trw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on trw_submit_feedback? +

Register the Trw MCP server in PolicyLayer and add a rule for trw_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 Trw. Nothing to install.

What risk level is trw_submit_feedback? +

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

Can I rate-limit trw_submit_feedback? +

Yes. Add a rate_limit block to the trw_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 trw_submit_feedback completely? +

Set action: deny in the PolicyLayer policy for trw_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 trw_submit_feedback? +

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