AI agents call get_weekly_summary 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 aggregated health/fitness data from Garmin Connect without creating, modifying, deleting, or executing operations. It is a pure query operation with no side effects, fitting the Read category. Severity is low because unauthorized access to personal health metrics carries minimal blast radius compared to other risk categories.
From the tool's definition Tool description states it retrieves 'Weekly aggregates for a single metric' with no modification capability. Server description explicitly notes tools are 'read-only'. Tool name 'get_' prefix indicates data retrieval.
Attacks that exploit this kind of access
Weekly aggregates for a single metric. 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_weekly_summary: 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_weekly_summary 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_weekly_summary 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_weekly_summary. 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_weekly_summary 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 →