mementos_storage_feedback · Mementos MCP: Risk & Policy

WHAT IT DOES

What mementos_storage_feedback does on Mementos

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

WHY IT NEEDS A POLICY

Why mementos_storage_feedback needs a policy

This tool creates or modifies feedback records within the mementos storage system. While the action is reversible (feedback can be updated or deleted via sibling tools like bulk_forget or entity_delete), it modifies persistent state in the memory system.

From the tool's definition The tool name contains 'save' action ("Save feedback") and the description states "Save feedback for mementos", indicating it creates or modifies feedback data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mementos_storage_feedback Rate-limited

mementos_storage_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": {
    "mementos_storage_feedback": {
      "limits": [
        {
          "counter": "mementos_storage_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 Mementos, so you can run agents against it safely.

FAQ

Questions about mementos_storage_feedback

What does the mementos_storage_feedback tool do? +

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

How do I enforce a policy on mementos_storage_feedback? +

Register the Mementos MCP server in PolicyLayer and add a rule for mementos_storage_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 Mementos. Nothing to install.

What risk level is mementos_storage_feedback? +

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

Can I rate-limit mementos_storage_feedback? +

Yes. Add a rate_limit block to the mementos_storage_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 mementos_storage_feedback completely? +

Set action: deny in the PolicyLayer policy for mementos_storage_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 mementos_storage_feedback? +

mementos_storage_feedback is provided by the Mementos MCP server (@hasna/mementos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.