获取某天的 HRV（心率变异性）数据
AI agents call get_hrv to retrieve information from Garmin Connect China MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query operation that retrieves historical health metrics (HRV data) from Garmin Connect. It has no side effects, does not modify data, and does not trigger external actions. The entire server is read-only for accessing personal fitness data. Low severity due to limited blast radius—returning health metrics to an AI agent poses minimal operational risk.
From the tool's definition Tool name 'get_hrv' and description '获取某天的 HRV（心率变异性）数据' (Retrieve a day's HRV heart rate variability data) indicate a retrieval operation. All sibling tools are read-only (get_* pattern): get_activities, get_devices, get_earned_badges, etc.
Attacks that exploit this kind of access
获取某天的 HRV（心率变异性）数据. It is categorised as a Read tool in the Garmin Connect China MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Garmin Connect China MCP Server MCP server in PolicyLayer and add a rule for get_hrv: 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 Connect China MCP Server. Nothing to install.
get_hrv 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 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. 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 is provided by the Garmin Connect China MCP Server MCP server (xinyuxinyuxintaihaohao/garmin-cn-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 →