Query workouts for a date range
AI agents call query_workouts to retrieve information from Zepp Life MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical workout data from Zepp Life without creating, modifying, or deleting anything. It is a read-only query operation with minimal blast radius if misused—an AI agent could only access or expose the user's workout information, not alter health data or perform destructive operations.
From the tool's definition Tool name 'query_workouts' and description 'Query workouts for a date range' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Query workouts for a date range. It is categorised as a Read tool in the Zepp Life MCP MCP Server, which means it retrieves data without modifying state.
Register the Zepp Life MCP server in PolicyLayer and add a rule for query_workouts: 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 Zepp Life MCP. Nothing to install.
query_workouts 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 query_workouts 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 query_workouts. 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.
query_workouts is provided by the Zepp Life MCP server (kubulashvili/zepp-life-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 →