AI agents call food_by_category to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
page | number | — | |
category | string | Yes |
Parameters from the server's own tool schema.
The tool retrieves data (food products) filtered by category from a public database. There is no creation, modification, deletion, or execution of code. The operation is purely informational and read-only, with no capability to alter data or trigger external actions.
From the tool's definition Tool performs a 'Get' operation to retrieve food products by category from Open Food Facts, which is a read-only query with no side effects.
Attacks that exploit this kind of access
Get food products by category from Open Food Facts. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
food_by_category accepts 2 parameters: page, category. Required: category. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for food_by_category: 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 UnClick. Nothing to install.
food_by_category is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the food_by_category 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 food_by_category. 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.
food_by_category is provided by the UnClick MCP server (@unclick/mcp-server). 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 →