Upload, delete, or modify activities
AI agents call manage_activities to permanently remove resources in Garmin MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Because the tool supports deletion of activities (which is irreversible), it must be classified under Destructive per the severity hierarchy. It also supports write operations (upload, modify), but Destructive takes precedence. Misuse by an AI agent could result in permanent loss of fitness/activity data the user cannot recover.
From the tool's definition 'delete' in 'Upload, delete, or modify activities' — the tool explicitly supports irreversible deletion of activity records
Attacks that exploit this kind of access
Upload, delete, or modify activities. It is categorised as a Destructive tool in the Garmin MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Garmin MCP Server MCP server in PolicyLayer and add a rule for manage_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 MCP Server. Nothing to install.
manage_activities is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_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 manage_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.
manage_activities is provided by the Garmin MCP Server MCP server (j4sun/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 →