Patch a food.
AI agents use update_food to create or update resources in Mcp Mealie — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Mealie environment.
This tool modifies existing food taxonomy data in the Mealie system. As a PATCH operation, it updates food properties reversibly without deleting or destroying data. It does not execute arbitrary code, move money, or perform destructive operations. The blast radius is limited to the food taxonomy metadata and any meal plans or recipes that reference the updated food, making it Write category with medium severity.
From the tool's definition Patch a food - 'Patch' indicates a partial modification/update operation on a food resource in the Mealie taxonomy system. The verb 'update' in the tool name and 'Patch' in the description both signify reversible data modification.
Attacks that exploit this kind of access
Patch a food. It is categorised as a Write tool in the Mcp Mealie MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Mealie MCP server in PolicyLayer and add a rule for update_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 Mcp Mealie. Nothing to install.
update_food 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 update_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.
Set action: deny in the PolicyLayer policy for update_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.
update_food is provided by the Mcp Mealie MCP server (obrien-matthew/mcp-mealie). 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 →