memory_autoinject_config · Mementos MCP: Risk & Policy

WHAT IT DOES

What memory_autoinject_config does on Mementos

AI agents use memory_autoinject_config 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_autoinject_config needs a policy

This tool modifies configuration settings that govern how memory is injected into agent operations. While changes are reversible (can be reconfigured), altering throttle, debounce, and rate limits could disrupt system behavior or cause unintended memory injection patterns.

From the tool's definition Tool description states it can 'Get or set auto-inject orchestrator config', with 'set' indicating modification capability. Controls configuration parameters including 'throttle, debounce, rate limits, and similarity thresholds'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_autoinject_config Rate-limited

memory_autoinject_config 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_autoinject_config": {
      "limits": [
        {
          "counter": "memory_autoinject_config_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_autoinject_config

What does the memory_autoinject_config tool do? +

Get or set auto-inject orchestrator config (channel-based memory push). Controls throttle, debounce, rate limits, and similarity thresholds for proactive memory injection. 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_autoinject_config? +

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

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

Can I rate-limit memory_autoinject_config? +

Yes. Add a rate_limit block to the memory_autoinject_config 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_autoinject_config completely? +

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

memory_autoinject_config 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.