log_food · Nutrition MCP: Risk & Policy

WHAT IT DOES

What log_food does on Nutrition MCP

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

WHY IT NEEDS A POLICY

Why log_food needs a policy

This tool writes a new food entry to local filesystem storage. It creates data (does not delete or overwrite existing records irreversibly), making Write the appropriate category. Severity is medium because misuse could corrupt a user's nutrition tracking history, but there is no financial, destructive, or code-execution risk.

From the tool's definition 'Store a confirmed food entry' — creates a new persistent log record with calorie and protein data; reversible via the sibling 'undo_last_log' tool.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_food Rate-limited

log_food 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": {
    "log_food": {
      "limits": [
        {
          "counter": "log_food_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 Nutrition MCP, so you can run agents against it safely.

FAQ

Questions about log_food

What does the log_food tool do? +

Store a confirmed food entry. The agent supplies calories and protein (estimated with its own knowledge or web search). Requires userConfirmed: true. It is categorised as a Write tool in the Nutrition MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on log_food? +

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

What risk level is log_food? +

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

Can I rate-limit log_food? +

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

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

log_food is provided by the Nutrition MCP server (ronkommoji/nutrition-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.