AI agents call get_fitness_metrics 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.
The tool appears to retrieve fitness metrics data without modifying, deleting, or executing external operations. The 'get_' prefix and alignment with other read-only sibling tools on this server establish it as a Read operation. Severity is low since fitness metrics are personal health data with limited blast radius if exposed to an AI agent.
From the tool's definition Server description states tools are 'read-only' and the server enables querying health metrics. Tool name 'get_fitness_metrics' follows the 'get_*' pattern consistent with sibling read-only tools (get_activity_details, get_body_battery, get_daily_briefing,…
Attacks that exploit this kind of access
get_fitness_metrics. 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_fitness_metrics: 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_fitness_metrics 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_fitness_metrics 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_fitness_metrics. 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_fitness_metrics 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 →