AI agents call get_body_composition 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 body composition data from Garmin Connect without modifying, executing, or destroying any data. While the tool description is empty, the naming pattern and server context strongly indicate it is a read operation that queries health metrics. The blast radius of misuse is low—an agent could only retrieve personal health information. No financial, destructive, or execution actions are possible.
From the tool's definition Tool name 'get_body_composition' is a read-only accessor; server description explicitly states 'read-only MCP tools'. Sibling tools follow the pattern of data retrieval (get_activity_details, get_fitness_metrics, get_personal_records, etc.).
Attacks that exploit this kind of access
get_body_composition. 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_body_composition: 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_body_composition 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_body_composition 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_body_composition. 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_body_composition 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 →