AI agents call search_foods to retrieve information from USDA Nutrition MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the USDA database without creating, modifying, deleting, or executing operations. Misuse would only result in excessive queries or information disclosure, which pose minimal risk. Severity is low because the blast radius of an AI agent querying food data is negligible.
From the tool's definition Tool name 'search_foods' and description 'Search for foods in the USDA database' indicate a query operation with no data modification or destructive capability.
Documented attack patterns abuse exactly the kind of access search_foods gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and USDA Nutrition MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_foods:
{
"version": "1",
"default": "deny",
"tools": {
"search_foods": {}
}
}search_foods 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.
Search for foods in the USDA database. It is categorised as a Read tool in the USDA Nutrition MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USDA Nutrition MCP Server MCP server in PolicyLayer and add a rule for search_foods: 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 USDA Nutrition MCP Server. Nothing to install.
search_foods 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 search_foods 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 search_foods. 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.
search_foods is provided by the USDA Nutrition MCP Server MCP server (zen-apps/mcp-nutrition-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from USDA Nutrition MCP Server, 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.
6 USDA Nutrition MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.