memory_flag · Mementos MCP: Risk & Policy

WHAT IT DOES

What memory_flag does on Mementos

AI agents use memory_flag 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 memory_flag needs a policy

This tool modifies metadata on an existing memory record (adding or clearing a flag). It is a reversible write operation — flags can be set or cleared — with no code execution, deletion, or financial implications. Misuse is low-severity since it only affects how memories are surfaced, not their content or existence.

From the tool's definition Flag a memory for attention: needs-review, outdated, verify, or any custom flag. Pass flag=null to clear.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_flag Rate-limited

memory_flag 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_flag": {
      "limits": [
        {
          "counter": "memory_flag_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 memory_flag

What does the memory_flag tool do? +

Flag a memory for attention: needs-review, outdated, verify, or any custom flag. Flagged memories surface at the top of memory_context. Pass flag=null to clear. 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 memory_flag? +

Register the Mementos MCP server in PolicyLayer and add a rule for memory_flag: 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 memory_flag? +

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

Can I rate-limit memory_flag? +

Yes. Add a rate_limit block to the memory_flag 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_flag completely? +

Set action: deny in the PolicyLayer policy for memory_flag. 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_flag? +

memory_flag 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.