get_activity_zones
AI agents call get_activity_zones 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, consistency with other sibling tools, and the server's stated purpose of 'enabling training analysis' all point to a read-only data retrieval function. Even with an empty description, there is no indication this tool modifies, deletes, or executes operations. Low severity because retrieving personal fitness zone data poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'get_activity_zones' with prefix 'get_' indicates data retrieval. Sibling tools on the server (get_activities, get_fitness, get_goals, etc.) are all read-only queries of Garmin Connect data.
Attacks that exploit this kind of access
get_activity_zones. 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_activity_zones: 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_activity_zones 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_activity_zones 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_activity_zones. 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_activity_zones 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 →