Create a recipe in your Old Family Recipe cookbook. Include ingredients, instructions,
AI agents use recipe_create 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.
This tool adds new data to the cookbook application. Creation is a Write operation because recipes can be updated (evidenced by the sibling tool 'recipe_update') or deleted (evidenced by 'recipe_delete'), making the action reversible.
From the tool's definition Tool name is 'recipe_create' and description states 'Create a recipe in your Old Family Recipe cookbook' — this creates new data (a recipe record) that is reversibly modifiable.
Attacks that exploit this kind of access
Create a recipe in your Old Family Recipe cookbook. Include ingredients, instructions,. 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.
Register the Old Family Recipe MCP server in PolicyLayer and add a rule for recipe_create: 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.
recipe_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the recipe_create 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.
Set action: deny in the PolicyLayer policy for recipe_create. 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.
recipe_create 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →