Remove a previously logged water entry by its logId (from log_water output or from get_food_log.water.water[].logId).
AI agents call delete_water_log to permanently remove resources in Fitbit Googlehealth — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes user health data (water intake logs). Deletion is permanent and cannot be recovered. While the blast radius is limited to a single log entry rather than systemic data, it still qualifies as Destructive per the definitions.
From the tool's definition Tool name 'delete_water_log' and description explicitly states 'Remove a previously logged water entry' - a deletion operation that cannot be undone.
Attacks that exploit this kind of access
Remove a previously logged water entry by its logId (from log_water output or from get_food_log.water.water[].logId). It is categorised as a Destructive tool in the Fitbit Googlehealth MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Fitbit Googlehealth MCP server in PolicyLayer and add a rule for delete_water_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 Fitbit Googlehealth. Nothing to install.
delete_water_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 delete_water_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 delete_water_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.
delete_water_log is provided by the Fitbit Googlehealth MCP server (tachibanayu24/fitbit-googlehealth-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 →