Get AI-generated insights about products (detected labels, categories, ingredients issues, etc.)
AI agents call getProductInsights to retrieve information from OpenFoodFacts-mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries the OpenFoodFacts database and returns computed insights without creating, modifying, or deleting any data. The tool's purpose is information retrieval and analysis of publicly available food product data. The severity is low as misuse would only result in gathering information without side effects or impact on data integrity.
From the tool's definition Tool retrieves and analyzes existing product data ('Get AI-generated insights about products'), providing information about detected labels, categories, and ingredients. No modification, deletion, or execution of external operations occurs.
Documented attack patterns abuse exactly the kind of access getProductInsights gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenFoodFacts-mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for getProductInsights:
{
"version": "1",
"default": "deny",
"tools": {
"getProductInsights": {}
}
} getProductInsights is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get AI-generated insights about products (detected labels, categories, ingredients issues, etc.). It is categorised as a Read tool in the OpenFoodFacts-mcp MCP Server, which means it retrieves data without modifying state.
Register the OpenFoodFacts- MCP server in PolicyLayer and add a rule for getProductInsights: 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 OpenFoodFacts-mcp. Nothing to install.
getProductInsights 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 getProductInsights 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 getProductInsights. 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.
getProductInsights is provided by the OpenFoodFacts- MCP server (jagjeevanak/openfoodfacts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenFoodFacts-mcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 OpenFoodFacts-mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.