save_note · Memory MCP: Risk & Policy

WHAT IT DOES

What save_note does on Memory

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

WHY IT NEEDS A POLICY

Why save_note needs a policy

This tool creates or modifies notes in a local knowledge store. It is reversible (notes can be edited or deleted later), so it is Write rather than Destructive. The severity is medium because misuse by an AI agent could result in unwanted notes being saved to the user's personal knowledge base, potentially polluting search results or creating false records, but the impact is limited to this local system and…

From the tool's definition Tool name 'save_note' combined with context of a note-taking/memory MCP server indicates creation or modification of note data. The empty description limits precision, but 'save' typically means persist/create/update operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_note Rate-limited

save_note 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": {
    "save_note": {
      "limits": [
        {
          "counter": "save_note_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 Memory, so you can run agents against it safely.

FAQ

Questions about save_note

What does the save_note tool do? +

save_note. It is categorised as a Write tool in the Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_note? +

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

What risk level is save_note? +

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

Can I rate-limit save_note? +

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

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

save_note is provided by the Memory MCP server (shaktisinhchavda/memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.