Remove the most recent food log entry, optionally constrained to a specific date.
AI agents call undo_last_log to permanently remove resources in Nutrition MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool removes/deletes a food log entry. While it is scoped to the most recent entry (limiting blast radius), deletion of logged data is irreversible, placing it in the Destructive category. Severity is medium because only one entry is affected at a time and the data is personal nutrition logs rather than critical system data.
From the tool's definition "Remove the most recent food log entry" — permanently deletes a log record
Attacks that exploit this kind of access
Remove the most recent food log entry, optionally constrained to a specific date. It is categorised as a Destructive tool in the Nutrition MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nutrition MCP server in PolicyLayer and add a rule for undo_last_log: 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.
undo_last_log is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the undo_last_log 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 undo_last_log. 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.
undo_last_log 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 →