Get sleep stages and metrics for a given date.
AI agents call get_sleep_data to retrieve information from Mcp 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 sleep data from Garmin Connect without modifying, executing operations, or performing destructive actions. It is a straightforward data query operation with no side effects. The low severity reflects minimal blast radius even if misused by an AI agent, as it only exposes personal health metrics already accessible through the user's own Garmin account.
From the tool's definition Tool name 'get_sleep_data' and server description explicitly states 'read-only access to daily health metrics'. The function retrieves sleep stages and metrics with no modification capability.
Attacks that exploit this kind of access
Get sleep stages and metrics for a given date. It is categorised as a Read tool in the Mcp Garmin MCP Server, which means it retrieves data without modifying state.
Register the Mcp Garmin MCP server in PolicyLayer and add a rule for get_sleep_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 Mcp Garmin. Nothing to install.
get_sleep_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_sleep_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_sleep_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_sleep_data is provided by the Mcp Garmin MCP server (obrien-matthew/mcp-garmin). 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 →