获取运动的分段数据（每公里配速等）
AI agents call get_activity_splits 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 tool retrieves historical fitness data splits from Garmin—a read-only query with no side effects. It fits the 'Read' category (retrieves or queries data). Severity is low because access to personal health metrics, while privacy-sensitive, carries no immediate operational risk if misused by an agent.
From the tool's definition Tool name 'get_activity_splits' and description indicate retrieval of activity segment data (split times, pace per kilometer, etc.). No modification, deletion, or execution capabilities are described.
Attacks that exploit this kind of access
获取运动的分段数据（每公里配速等）. 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_activity_splits: 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_activity_splits 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_activity_splits 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_activity_splits. 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_activity_splits 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 →