Import a recipe from a photo of a handwritten recipe card.
AI agents use recipe_import_image 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 reads an image input and creates a new recipe record in the cookbook app. This is clearly a Write operation (create data reversibly), not Read (it transforms the image into stored data rather than just querying), Execute (no arbitrary code execution or external side effects), Destructive (the action is reversible), or Financial.
From the tool's definition The tool 'recipe_import_image' creates new recipe data by extracting content from a photo of a handwritten card. The description states it will 'Import a recipe' which results in data being added to the system.
Attacks that exploit this kind of access
Import a recipe from a photo of a handwritten recipe card. 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_import_image: 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_import_image 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_import_image 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_import_image. 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_import_image 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 →