fitatu_search_food
AI agents call fitatu_search_food to retrieve information from Fitatu Wrapper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve and query data without modifying, deleting, or executing external commands. This is a straightforward Read action with low severity since it only accesses nutrition/food data. Confidence is reduced slightly due to the empty tool description, but the server description and naming provide sufficient context.
From the tool's definition Tool name 'fitatu_search_food' indicates a search operation. Server description states the tool enables 'food search' as a read operation alongside other non-destructive actions like login and daily nutrition read.
Attacks that exploit this kind of access
fitatu_search_food. It is categorised as a Read tool in the Fitatu Wrapper MCP Server, which means it retrieves data without modifying state.
Register the Fitatu Wrapper MCP server in PolicyLayer and add a rule for fitatu_search_food: 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 Fitatu Wrapper. Nothing to install.
fitatu_search_food 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 fitatu_search_food 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 fitatu_search_food. 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.
fitatu_search_food is provided by the Fitatu Wrapper MCP server (kymylyy/fitatu-wrapper). 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 →