memento_toggle_precognition · Memento MCP: Risk & Policy

WHAT IT DOES

What memento_toggle_precognition does on Memento

AI agents invoke memento_toggle_precognition to trigger actions in Memento. 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 memento_toggle_precognition needs a policy

Toggling a background daemon is an Execute-category action: it starts or stops an autonomous background process. The [DEPRECATED] tag and vague description reduce confidence, but starting/stopping daemons can have broad side effects on system behavior. Severity is medium given the blast radius of enabling/disabling autonomous background intelligence in an AI memory middleware.

From the tool's definition 'Toggle the Pre-cognitive Intervention background daemon' — enables or disables a background daemon process

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memento_toggle_precognition Rate-limited

memento_toggle_precognition 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": {
    "memento_toggle_precognition": {
      "limits": [
        {
          "counter": "memento_toggle_precognition_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 Memento, so you can run agents against it safely.

FAQ

Questions about memento_toggle_precognition

What does the memento_toggle_precognition tool do? +

[DEPRECATED] Toggle the Pre-cognitive Intervention background daemon. It is categorised as a Execute tool in the Memento MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on memento_toggle_precognition? +

Register the Memento MCP server in PolicyLayer and add a rule for memento_toggle_precognition: 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 Memento. Nothing to install.

What risk level is memento_toggle_precognition? +

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

Can I rate-limit memento_toggle_precognition? +

Yes. Add a rate_limit block to the memento_toggle_precognition 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 memento_toggle_precognition completely? +

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

memento_toggle_precognition is provided by the Memento MCP server (joyciakira/memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.