percept_feedback · Perceptdot MCP: Risk & Policy

WHAT IT DOES

What percept_feedback does on Perceptdot

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

WHY IT NEEDS A POLICY

Why percept_feedback needs a policy

This tool submits user feedback (a rating and comment) to an external service, which is a reversible write/post action. The consequence of misuse is minimal — at worst, spammy feedback is submitted — making severity low. The 'unlock 100 more free calls' aspect hints at a minor entitlement side effect, but it does not constitute a financial transaction.

From the tool's definition Submit feedback to unlock 100 more free calls. Rate 1-5 and leave a comment (max 150 chars).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

percept_feedback Rate-limited

percept_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": {
    "percept_feedback": {
      "limits": [
        {
          "counter": "percept_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 Perceptdot, so you can run agents against it safely.

FAQ

Questions about percept_feedback

What does the percept_feedback tool do? +

Submit feedback to unlock 100 more free calls. Rate 1-5 and leave a comment (max 150 chars). It is categorised as a Write tool in the Perceptdot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on percept_feedback? +

Register the Perceptdot MCP server in PolicyLayer and add a rule for percept_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 Perceptdot. Nothing to install.

What risk level is percept_feedback? +

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

Can I rate-limit percept_feedback? +

Yes. Add a rate_limit block to the percept_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 percept_feedback completely? +

Set action: deny in the PolicyLayer policy for percept_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 percept_feedback? +

percept_feedback is provided by the Perceptdot MCP server (perceptdot/percept). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.