Record a weight reading. BMI is computed by Fitbit if a height is on file.
AI agents use log_weight to create or update resources in Fitbit Googlehealth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fitbit Googlehealth environment.
This tool writes a weight measurement to the user's Fitbit account. It is a data creation action with no irreversible consequences, financial implications, or code execution. The existence of a delete_weight_log sibling confirms the action is reversible.
From the tool's definition 'Record a weight reading' — creates a new weight log entry in Fitbit; reversible (sibling tool delete_weight_log exists).
Attacks that exploit this kind of access
Record a weight reading. BMI is computed by Fitbit if a height is on file. It is categorised as a Write tool in the Fitbit Googlehealth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fitbit Googlehealth MCP server in PolicyLayer and add a rule for log_weight: 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.
log_weight is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the log_weight 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 log_weight. 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.
log_weight 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 →