Low Risk

getInsightTypes

Get a summary of available AI insight types in Robotoff

How to control getInsightTypes ↓

What getInsightTypes does on OpenFoodFacts-mcp

AI agents call getInsightTypes 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.

Low Risk

Why getInsightTypes needs a policy

This tool performs a straightforward data retrieval operation—fetching a list or summary of insight types from the Robotoff system. It has no side effects, does not execute external code, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal, as an AI agent could only retrieve information about what insight types exist, which poses no security or operational risk.

From the tool's definition Tool name 'getInsightTypes' and description 'Get a summary of available AI insight types' indicate a query operation that retrieves metadata about available insights without modifying, executing, or deleting any data.

Documented attack patterns abuse exactly the kind of access getInsightTypes gives an agent:

How to control getInsightTypes

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 getInsightTypes:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "getInsightTypes": {}
  }
}

getInsightTypes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register OpenFoodFacts-mcp — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about getInsightTypes

What does the getInsightTypes tool do? +

Get a summary of available AI insight types in Robotoff. It is categorised as a Read tool in the OpenFoodFacts-mcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on getInsightTypes? +

Register the OpenFoodFacts- MCP server in PolicyLayer and add a rule for getInsightTypes: 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.

What risk level is getInsightTypes? +

getInsightTypes is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit getInsightTypes? +

Yes. Add a rate_limit block to the getInsightTypes 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.

How do I block getInsightTypes completely? +

Set action: deny in the PolicyLayer policy for getInsightTypes. 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.

What MCP server provides getInsightTypes? +

getInsightTypes 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.

Enforce policy on every OpenFoodFacts-mcp tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.