Get stress data
AI agents call get_stress_data to retrieve information from Garmin 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 existing stress data from Garmin Connect without modifying, deleting, or executing operations. While stress data could be considered sensitive health information, the tool itself performs no side effects or destructive actions. Classification as Read is appropriate for health data retrieval endpoints.
From the tool's definition Tool name 'get_stress_data' and description 'Get stress data' indicate a retrieval operation. The verb 'get' and the absence of write, delete, or execute semantics confirm this is a read-only query.
Attacks that exploit this kind of access
Get stress data. It is categorised as a Read tool in the Garmin MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Garmin MCP Server MCP server in PolicyLayer and add a rule for get_stress_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. Nothing to install.
get_stress_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_stress_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_stress_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_stress_data is provided by the Garmin MCP Server MCP server (shubhaankar-sharma/garmin-mcp-railway). 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 →