Nightly SpO2 averages (min / avg / max) across a date range. Cached 1h.
AI agents call get_spo2 to retrieve information from Fitbit Googlehealth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical health metrics (SpO2 oxygen saturation data) from the user's Fitbit account. It performs a read-only query of existing data with no ability to modify, delete, or execute actions.
From the tool's definition Tool name is 'get_spo2' and description states it retrieves 'Nightly SpO2 averages (min / avg / max) across a date range' with caching. The verb 'get' and passive retrieval language indicate data querying without side effects.
Attacks that exploit this kind of access
Nightly SpO2 averages (min / avg / max) across a date range. Cached 1h. It is categorised as a Read tool in the Fitbit Googlehealth MCP Server, which means it retrieves data without modifying state.
Register the Fitbit Googlehealth MCP server in PolicyLayer and add a rule for get_spo2: 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.
get_spo2 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 get_spo2 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 get_spo2. 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.
get_spo2 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 →