dietary_prefs · Personal Brain MCP: Risk & Policy

WHAT IT DOES

What dietary_prefs does on Personal Brain

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

WHY IT NEEDS A POLICY

Why dietary_prefs needs a policy

This tool retrieves and modifies personal dietary information. While it can read data (low risk), the 'modify' capability makes it a Write operation. Severity is medium because misuse could corrupt important health records (e.g., removing a documented allergy) that affect meal planning and health decisions, though it doesn't directly cause physical harm or irreversible destruction.

From the tool's definition Tool description states 'Get or modify dietary preferences' — the 'modify' verb indicates data modification capability. Dietary preferences (allergies, dislikes, restrictions) are personal health-related data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dietary_prefs Rate-limited

dietary_prefs 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": {
    "dietary_prefs": {
      "limits": [
        {
          "counter": "dietary_prefs_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 Personal Brain, so you can run agents against it safely.

FAQ

Questions about dietary_prefs

What does the dietary_prefs tool do? +

Get or modify dietary preferences for a person (allergies, dislikes, restrictions). Use before menu-planning for guests. It is categorised as a Write tool in the Personal Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on dietary_prefs? +

Register the Personal Brain MCP server in PolicyLayer and add a rule for dietary_prefs: 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 Personal Brain. Nothing to install.

What risk level is dietary_prefs? +

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

Can I rate-limit dietary_prefs? +

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

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

dietary_prefs is provided by the Personal Brain MCP server (phantomts/personal-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.