recipe_update · Old Family Recipe MCP: Risk & Policy

WHAT IT DOES

What recipe_update does on Old Family Recipe

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

WHY IT NEEDS A POLICY

Why recipe_update needs a policy

This tool modifies existing recipes reversibly (a user can correct a recipe, change measurements, or adjust instructions without permanent loss). It is not destructive (deletion is handled by recipe_delete), not read-only, and does not involve financial transactions or code execution.

From the tool's definition Tool name is 'recipe_update' and description states 'Update an existing recipe in your cookbook.' The verb 'update' indicates modification of existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

recipe_update Rate-limited

recipe_update 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": {
    "recipe_update": {
      "limits": [
        {
          "counter": "recipe_update_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 Old Family Recipe, so you can run agents against it safely.

FAQ

Questions about recipe_update

What does the recipe_update tool do? +

Update an existing recipe in your cookbook. It is categorised as a Write tool in the Old Family Recipe MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on recipe_update? +

Register the Old Family Recipe MCP server in PolicyLayer and add a rule for recipe_update: 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 Old Family Recipe. Nothing to install.

What risk level is recipe_update? +

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

Can I rate-limit recipe_update? +

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

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

recipe_update is provided by the Old Family Recipe MCP server (oldfamilyrecipe/ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.