Get detailed metrics for an activity (laps, charts, etc.).
AI agents call get_activity_details to retrieve information from Mcp Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries activity data without side effects. The server is explicitly read-only, and all sibling tools follow the read-only pattern (get_activities, get_body_composition, etc.). Misuse would only result in unauthorized data access, not irreversible changes or financial impact.
From the tool's definition Tool name 'get_activity_details' and server description explicitly states 'read-only access'. The tool retrieves detailed metrics for activities (laps, charts, etc.) with no capability to modify or delete data.
Attacks that exploit this kind of access
Get detailed metrics for an activity (laps, charts, etc.). It is categorised as a Read tool in the Mcp Garmin MCP Server, which means it retrieves data without modifying state.
Register the Mcp Garmin MCP server in PolicyLayer and add a rule for get_activity_details: 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 Mcp Garmin. Nothing to install.
get_activity_details 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_details 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_details. 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_details is provided by the Mcp Garmin MCP server (obrien-matthew/mcp-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 →