memory_reflect · Mementos MCP: Risk & Policy

WHAT IT DOES

What memory_reflect does on Mementos

AI agents use memory_reflect 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_reflect needs a policy

This tool creates new memory entries (lessons learned) based on reflection analysis. It modifies the memory state by adding new linked memories, making it a Write operation. It is reversible via the bulk_forget or entity_delete tools available on the same server.

From the tool's definition Tool writes structured lessons back as linked memories to the memory system. Described as 'write structured lessons back as linked memories' with a dry_run option for preview, indicating data creation/modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_reflect Rate-limited

memory_reflect 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_reflect": {
      "limits": [
        {
          "counter": "memory_reflect_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_reflect

What does the memory_reflect tool do? +

Reflect on a session, task, or range with an LLM-judge critic and write structured lessons back as linked memories. Use dry_run=true to preview. 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_reflect? +

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

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

Can I rate-limit memory_reflect? +

Yes. Add a rate_limit block to the memory_reflect 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_reflect completely? +

Set action: deny in the PolicyLayer policy for memory_reflect. 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_reflect? +

memory_reflect 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.