AI agents call get_recent_activities to retrieve information from Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical activity information from Garmin Connect without creating, modifying, executing commands, or deleting data. It is a straightforward read operation with no side effects or security-sensitive capabilities. The low severity reflects minimal risk even if misused—an AI agent reading user activity data poses no financial, destructive, or execution-based harm.
From the tool's definition Tool name 'get_recent_activities' and server description explicitly states 'read-only MCP tools'. The function retrieves activity data (type, duration, distance, heart rate) with no modification or execution capability.
Attacks that exploit this kind of access
List recent activities with type, duration, distance, and average heart rate. It is categorised as a Read tool in the Garmin MCP Server, which means it retrieves data without modifying state.
Register the Garmin MCP server in PolicyLayer and add a rule for get_recent_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 Garmin. Nothing to install.
get_recent_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_recent_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_recent_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_recent_activities is provided by the Garmin MCP server (tyler-irving/garmin-mcp). 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 →