save_note · MCP AI Research Assistant MCP: Risk & Policy

WHAT IT DOES

What save_note does on MCP AI Research Assistant

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

WHY IT NEEDS A POLICY

Why save_note needs a policy

The tool creates or modifies note data persistently. It is reversible (notes can be updated or deleted by other means), so it is Write rather than Destructive. The severity is low because notes are typically non-critical research data with no external side effects or blast radius. Confidence is 0.9 (not higher only because the description is empty, leaving some ambiguity about exact behavior).

From the tool's definition Tool name 'save_note' indicates data creation/modification. Server context describes 'saving/retrieving notes', and tool is listed alongside read operations (get_notes, extract_key_points, summarize_text), positioning it as the write counterpart.

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 MCP AI Research Assistant, 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 MCP AI Research Assistant 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 MCP AI Research Assistant 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 MCP AI Research Assistant. 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 MCP AI Research Assistant MCP server (paneri11/mcp-ai-research-assistant). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.