get_fitness
AI agents call get_fitness 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 fitness data from Garmin Connect. Despite the empty description, the naming convention ('get_'), the context of sibling read-only query tools, and the server's stated purpose of data analysis (not modification) all indicate a passive Read operation. No modification, deletion, code execution, or financial action is implied.
From the tool's definition Tool name 'get_fitness' combined with sibling tools that are all Read operations (get_activities, get_gear, get_goals, etc.) and the server's purpose of 'enabling training analysis' and querying 'real metrics like HRV, training load'.
Attacks that exploit this kind of access
get_fitness. 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_fitness: 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_fitness 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 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. 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 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 →