report_feedback · Assetcache MCP: Risk & Policy

WHAT IT DOES

What report_feedback does on Assetcache

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

WHY IT NEEDS A POLICY

Why report_feedback needs a policy

This tool writes/records feedback data used for penalty-based learning. It creates or modifies data (feedback records) in a reversible way. It does not delete, execute code, or involve finances. Severity is low as misuse would at worst inject incorrect feedback signals into the recommendation system.

From the tool's definition '사용자 피드백을 기록한다 (페널티 학습 입력)' — records user feedback as penalty learning input

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

report_feedback Rate-limited

report_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": {
    "report_feedback": {
      "limits": [
        {
          "counter": "report_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 Assetcache, so you can run agents against it safely.

FAQ

Questions about report_feedback

What does the report_feedback tool do? +

추천 결과에 대한 사용자 피드백을 기록한다 (페널티 학습 입력). It is categorised as a Write tool in the Assetcache MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on report_feedback? +

Register the Assetcache MCP server in PolicyLayer and add a rule for report_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 Assetcache. Nothing to install.

What risk level is report_feedback? +

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

Can I rate-limit report_feedback? +

Yes. Add a rate_limit block to the report_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 report_feedback completely? +

Set action: deny in the PolicyLayer policy for report_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 report_feedback? +

report_feedback is provided by the Assetcache MCP server (v0o0v/assetcache-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.