get_gear
AI agents call get_gear 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.
The 'get_' prefix pattern across all sibling tools (get_activities, get_fitness, get_goals, etc.) and the MCP server's stated purpose of 'enabling training analysis' strongly suggest this is a data retrieval function. Garmin gear data (equipment information) is typically read-only information used for analysis. No description suggests potential for modification or execution.
From the tool's definition Tool named 'get_gear' with no description provided. Context from sibling tools (all prefixed 'get_') and server purpose indicates this retrieves Garmin Connect data about gear/equipment without modification.
Attacks that exploit this kind of access
get_gear. 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_gear: 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_gear 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_gear 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_gear. 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_gear 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 →