AI agents call fatsecret_get_recently_eaten to retrieve information from Fatsecret without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user food history data from the FatSecret API with no side effects or data modifications. It is a simple query operation that returns existing information about foods the user has recently consumed. No data is created, modified, or deleted.
From the tool's definition Tool name 'fatsecret_get_recently_eaten' and description 'Get the user' indicate retrieval of historical food consumption data without modification. The 'get' prefix and lack of any mutation verbs (create, edit, delete) confirm read-only behavior.
Attacks that exploit this kind of access
Get the user. It is categorised as a Read tool in the Fatsecret MCP Server, which means it retrieves data without modifying state.
Register the Fatsecret MCP server in PolicyLayer and add a rule for fatsecret_get_recently_eaten: 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 Fatsecret. Nothing to install.
fatsecret_get_recently_eaten 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 fatsecret_get_recently_eaten 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 fatsecret_get_recently_eaten. 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.
fatsecret_get_recently_eaten is provided by the Fatsecret MCP server (yurzs/fatsecret-mcp-server). 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 →