add_recipe · Personal Brain MCP: Risk & Policy

WHAT IT DOES

What add_recipe does on Personal Brain

AI agents use add_recipe 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 add_recipe needs a policy

This tool creates new recipe entries in a personal cookbook database. It is reversible (recipes can be edited or deleted later) and has no side effects beyond data creation. It does not execute code, delete data irreversibly, or move financial resources. The low severity reflects the minimal blast radius: an AI agent adding unwanted recipes causes minor inconvenience and can be easily corrected.

From the tool's definition Tool name 'add_recipe' and description 'Save a new recipe to your cookbook' indicate creation of new data records. The description specifies it includes ingredients, steps, source URL, and timing—all data fields being written to persistent storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_recipe Rate-limited

add_recipe 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": {
    "add_recipe": {
      "limits": [
        {
          "counter": "add_recipe_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 add_recipe

What does the add_recipe tool do? +

Save a new recipe to your cookbook. Includes ingredients (with quantities), steps, source URL, and timing. 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 add_recipe? +

Register the Personal Brain MCP server in PolicyLayer and add a rule for add_recipe: 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 add_recipe? +

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

Can I rate-limit add_recipe? +

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

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

add_recipe 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.