Get SpO2 (blood oxygen) data
AI agents call get_spo2_data to retrieve information from Garmin MCP Server for Poke without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves blood oxygen (SpO2) data, which is health/medical information and qualifies as a Read operation. However, severity is elevated to 'high' rather than 'low' because SpO2 data is sensitive health information that could enable health-related inferences, medical surveillance, or privacy violations if exposed to unauthorized actors or used inappropriately by an AI agent.
From the tool's definition Tool name and description: 'Get SpO2 (blood oxygen) data' — retrieves user health metrics without modifying data. SpO2 is sensitive personal health information.
Attacks that exploit this kind of access
Get SpO2 (blood oxygen) data. It is categorised as a Read tool in the Garmin MCP Server for Poke MCP Server, which means it retrieves data without modifying state.
Register the Garmin MCP Server for Poke MCP server in PolicyLayer and add a rule for get_spo2_data: 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 Garmin MCP Server for Poke. Nothing to install.
get_spo2_data 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_data 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_data. 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_data is provided by the Garmin MCP Server for Poke MCP server (theol0403/garmin-mcp-poke). 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 →