memory_sync_pull · Mementos MCP: Risk & Policy

WHAT IT DOES

What memory_sync_pull does on Mementos

AI agents use memory_sync_pull 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_sync_pull needs a policy

Pulling remote data into a local database constitutes data modification and creation of new records locally. While the operation itself is reversible (records can be deleted or updated), the blast radius is high because: (1) it modifies the local memory store without user-visible audit of what was pulled, (2) an AI agent misusing this could corrupt local memory state by pulling malicious or incorrect remote data,…

From the tool's definition Tool performs 'Pull memories from a remote mementos-serve instance into local DB', which imports external data into the local database. This is a reversible data modification operation (the pulled data can be updated or deleted separately).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

memory_sync_pull Rate-limited

memory_sync_pull 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_sync_pull": {
      "limits": [
        {
          "counter": "memory_sync_pull_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_sync_pull

What does the memory_sync_pull tool do? +

Pull memories from a remote mementos-serve instance into local DB. Set MEMENTOS_REMOTE_URL or pass url. 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_sync_pull? +

Register the Mementos MCP server in PolicyLayer and add a rule for memory_sync_pull: 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_sync_pull? +

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

Can I rate-limit memory_sync_pull? +

Yes. Add a rate_limit block to the memory_sync_pull 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_sync_pull completely? +

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

memory_sync_pull 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.