memory_auto_process · Mementos MCP: Risk & Policy

WHAT IT DOES

What memory_auto_process does on Mementos

AI agents invoke memory_auto_process to trigger actions in Mementos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why memory_auto_process needs a policy

The tool executes LLM-driven extraction logic (external process invocation) rather than simply reading or writing stored data. While it doesn't directly delete or move financial resources, it triggers computation with side effects that depend on the provided text and async parameter. The ability to control sync vs. async execution adds Execute-class risk.

From the tool's definition Tool description states it enqueues work for "async LLM memory extraction" and can "run synchronously and return extracted memories." This triggers external LLM operations and processes data through an AI system whose behavior depends on input arguments (the…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_auto_process Rate-limited

memory_auto_process stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_auto_process": {
      "limits": [
        {
          "counter": "memory_auto_process_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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_auto_process

What does the memory_auto_process tool do? +

Enqueue a conversation turn or text for async LLM memory extraction. Returns immediately (non-blocking). Set async=false to run synchronously and return extracted memories. It is categorised as a Execute tool in the Mementos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on memory_auto_process? +

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

memory_auto_process is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit memory_auto_process? +

Yes. Add a rate_limit block to the memory_auto_process 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_auto_process completely? +

Set action: deny in the PolicyLayer policy for memory_auto_process. 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_auto_process? +

memory_auto_process 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.