memory_retrieval_feedback · Munin Memory MCP: Risk & Policy

WHAT IT DOES

What memory_retrieval_feedback does on Munin Memory

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

WHY IT NEEDS A POLICY

Why memory_retrieval_feedback needs a policy

This tool writes feedback data to the memory system. It creates/modifies feedback records linked to retrieval events, which is a reversible write operation. It does not delete data, execute code, or involve financial transactions. Severity is low because misuse only results in incorrect feedback metadata being stored.

From the tool's definition Submit explicit feedback on retrieval quality... Also use to confirm good results. Auto-links to the most recent retrieval event in the current session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_retrieval_feedback Rate-limited

memory_retrieval_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": {
    "memory_retrieval_feedback": {
      "limits": [
        {
          "counter": "memory_retrieval_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 Munin Memory, so you can run agents against it safely.

FAQ

Questions about memory_retrieval_feedback

What does the memory_retrieval_feedback tool do? +

Submit explicit feedback on retrieval quality. Use after a search/query returned poor results, missed an expected entry, returned stale content, or ranked results badly. Also use to confirm good results. Auto-links to the most recent retrieval event in the current session. Owner-only. Feedback with missing_result + expected entry info feeds into benchmark ground truth candidates. It is categorised as a Write tool in the Munin Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_retrieval_feedback? +

Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_retrieval_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 Munin Memory. Nothing to install.

What risk level is memory_retrieval_feedback? +

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

Can I rate-limit memory_retrieval_feedback? +

Yes. Add a rate_limit block to the memory_retrieval_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 memory_retrieval_feedback completely? +

Set action: deny in the PolicyLayer policy for memory_retrieval_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 memory_retrieval_feedback? +

memory_retrieval_feedback is provided by the Munin Memory MCP server (magnus-gille/munin-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.