Search previous logged meals by raw text or parsed food item names.
AI agents call search_food_history to retrieve information from Nutrition MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical food logging data through a search interface. It performs a query operation on stored meal records and returns results without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an AI agent could only over-search or retrieve unwanted data, with no ability to alter the user's nutrition logs or trigger external systems.
From the tool's definition The tool description explicitly states it 'search[es] previous logged meals' with no mention of modification, deletion, or execution. The verb 'search' is a classic read operation that queries existing data without side effects.
Attacks that exploit this kind of access
Search previous logged meals by raw text or parsed food item names. It is categorised as a Read tool in the Nutrition MCP MCP Server, which means it retrieves data without modifying state.
Register the Nutrition MCP server in PolicyLayer and add a rule for search_food_history: 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 Nutrition MCP. Nothing to install.
search_food_history 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_food_history 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_food_history. 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_food_history is provided by the Nutrition MCP server (ronkommoji/nutrition-mcp). 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 →