fitatu_read_day_summary
AI agents call fitatu_read_day_summary 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.
This tool queries and retrieves a day's nutritional summary from the Fitatu service. It performs no side effects, creates no new data, and cannot modify or delete entries. Read operations have minimal blast radius even if misused by an AI agent—worst case is unnecessary API calls or information disclosure of the user's own nutrition data.
From the tool's definition Tool name 'fitatu_read_day' (listed sibling) and context of 'daily nutrition read' in server description indicate this retrieves nutritional data.
Attacks that exploit this kind of access
fitatu_read_day_summary. 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_read_day_summary: 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_read_day_summary 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_read_day_summary 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_read_day_summary. 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_read_day_summary 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 →