AI agents call getWaterLogs to retrieve information from FitBit MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical water consumption logs from Fitbit, a personal health metric. It has no side effects, cannot modify data, and poses minimal risk even if an AI agent calls it repeatedly or with unexpected parameters. The main concern would be data privacy/exposure, but that is an information security issue, not an operational risk category.
From the tool's definition Tool name 'getWaterLogs' indicates data retrieval. The pattern matches sibling tools (getActiveZoneMinutes, getActivities, getHeartRate, etc.) which are all read-only getters.
Documented attack patterns abuse exactly the kind of access getWaterLogs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FitBit MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for getWaterLogs:
{
"version": "1",
"default": "deny",
"tools": {
"getWaterLogs": {}
}
}getWaterLogs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
getWaterLogs. It is categorised as a Read tool in the FitBit MCP MCP Server, which means it retrieves data without modifying state.
Register the FitBit MCP server in PolicyLayer and add a rule for getWaterLogs: 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 MCP. Nothing to install.
getWaterLogs 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 getWaterLogs 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 getWaterLogs. 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.
getWaterLogs is provided by the FitBit MCP server (nitayrabi/fitbit-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FitBit MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 FitBit MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.