get_activities
AI agents call get_activities 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 strongly suggests this tool retrieves activity data without side effects. No evidence indicates it modifies, deletes, or executes operations. The tool fits the Read category as it queries user fitness/training data from Garmin Connect. Severity is low because unauthorized access to personal fitness metrics, while a privacy concern, does not enable destructive or financial harm.
From the tool's definition Tool name 'get_activities' indicates a retrieval operation. The description is empty, but the sibling tools on this server (get_activity_zones, get_bike_session, get_fitness, get_goals, etc.) all follow a 'get_*' pattern consistent with read-only data…
Attacks that exploit this kind of access
get_activities. 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_activities: 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_activities 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_activities 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_activities. 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_activities 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 →