AI agents call get_respiration 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 historical health metrics without modifying, executing, or deleting any data. It is a straightforward query operation on personal biometric data. Respiration rate is non-sensitive compared to financial or authentication data, and misuse would only expose personal health information rather than causing operational damage.
From the tool's definition Tool name 'get_respiration' and description explicitly state retrieval of daily respiration metrics (average, min, max, waking vs. sleeping averages). Server description confirms these are 'read-only MCP tools' with no side effects.
Attacks that exploit this kind of access
Daily respiration rate: average, min, max, and waking vs. sleeping averages. 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_respiration: 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_respiration 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_respiration 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_respiration. 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_respiration 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 →