AI agents use rename_workout to create or update resources in Garmin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Garmin environment.
This tool modifies data (the workout name) but does so reversibly without destructive effect. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), move money (would be Financial), or merely read data (would be Read).
From the tool's definition Tool description states 'Rename an existing workout' which modifies metadata of an existing resource. The operation is reversible (the old name can be restored by renaming again) and affects only the workout record itself, not the underlying activity data or…
Attacks that exploit this kind of access
Rename an existing workout in Garmin Connect (any sport type). Preserves all steps. It is categorised as a Write tool in the Garmin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Garmin MCP server in PolicyLayer and add a rule for rename_workout: 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.
rename_workout is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rename_workout 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 rename_workout. 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.
rename_workout is provided by the Garmin MCP server (marcelohensantos/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 →