retain_direct · Engram MCP: Risk & Policy

WHAT IT DOES

What retain_direct does on Engram

AI agents use retain_direct to create or update resources in Engram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Engram environment.

WHY IT NEEDS A POLICY

Why retain_direct needs a policy

This tool writes structured facts into the knowledge base. It is reversible in principle (the sibling 'forget' tool implies deletion is possible), so it does not qualify as Destructive. It does not execute code or move money. The blast radius is medium: an AI agent misusing this tool could pollute the knowledge base with false or misleading facts, but the damage is reversible.

From the tool's definition 'Store pre-extracted facts directly' — creates/writes structured data into the memory store

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retain_direct Rate-limited

retain_direct 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": {
    "retain_direct": {
      "limits": [
        {
          "counter": "retain_direct_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 Engram, so you can run agents against it safely.

FAQ

Questions about retain_direct

What does the retain_direct tool do? +

Store pre-extracted facts directly, skipping LLM extraction. Use when you already have structured facts. It is categorised as a Write tool in the Engram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on retain_direct? +

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

What risk level is retain_direct? +

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

Can I rate-limit retain_direct? +

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

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

retain_direct is provided by the Engram MCP server (reallyartificial/engram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.