memory_propose · Loom MCP: Risk & Policy

WHAT IT DOES

What memory_propose does on Loom

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

WHY IT NEEDS A POLICY

Why memory_propose needs a policy

This tool writes data (a draft memory entry) to a queue system without immediately committing it to persistent storage. The staged/draft nature and ratification workflow indicate the change is not yet finalized and can be rejected or modified before ratification, placing it in the Write category rather than Destructive.

From the tool's definition Tool description states it 'Stage[s] a DRAFT memory in the capture-propose queue for later ratification.' The use of 'stage' and 'propose' indicates the tool creates or modifies data in a queue system; the word 'DRAFT' and 'ratification' process suggests the…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_propose Rate-limited

memory_propose 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_propose": {
      "limits": [
        {
          "counter": "memory_propose_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 Loom, so you can run agents against it safely.

FAQ

Questions about memory_propose

What does the memory_propose tool do? +

Stage a DRAFT memory in the capture-propose queue for later ratification. It is categorised as a Write tool in the Loom 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_propose? +

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

What risk level is memory_propose? +

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

Can I rate-limit memory_propose? +

Yes. Add a rate_limit block to the memory_propose 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_propose completely? +

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

memory_propose is provided by the Loom MCP server (jbarket/loom). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.