AI agents call get_hrv_status to retrieve information from Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves health metrics (HRV/heart rate variability data) from Garmin Connect without creating, modifying, deleting, or executing any operations. It is a straightforward read operation querying historical biometric data. The low severity reflects minimal blast radius—exposure only discloses personal health information without enabling harmful actions.
From the tool's definition Server explicitly described as 'read-only MCP tools'. Tool name 'get_hrv_status' and description 'Current HRV status, baseline range, and the last 7 nights of readings' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Current HRV status, baseline range, and the last 7 nights of readings. It is categorised as a Read tool in the Garmin MCP Server, which means it retrieves data without modifying state.
Register the Garmin MCP server in PolicyLayer and add a rule for get_hrv_status: 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. Nothing to install.
get_hrv_status 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_hrv_status 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_hrv_status. 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_hrv_status is provided by the Garmin MCP server (tyler-irving/garmin-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 →