get_endurance_score
AI agents call get_endurance_score to retrieve information from Claude Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a metric (endurance score) from Garmin Connect. It is a read-only query operation with no side effects. The naming convention aligns with other data-retrieval tools on the server. Even if misused by an AI agent, it only exposes fitness metrics already available to the user, with minimal risk.
From the tool's definition Tool name 'get_endurance_score' follows the 'get_*' naming convention consistent with sibling tools (get_activities, get_fitness, get_goals, etc.).
Attacks that exploit this kind of access
get_endurance_score. It is categorised as a Read tool in the Claude Garmin MCP Server, which means it retrieves data without modifying state.
Register the Claude Garmin MCP server in PolicyLayer and add a rule for get_endurance_score: 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 Claude Garmin. Nothing to install.
get_endurance_score 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_endurance_score 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_endurance_score. 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_endurance_score is provided by the Claude Garmin MCP server (jack-abyss/claude-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 →