AI agents use update_swimming_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 creates or modifies data reversibly (matching Write category). It does not delete data (not Destructive), execute arbitrary code (not Execute), move money (not Financial), or merely read data (not Read). Severity is medium because misuse could corrupt or spam a user's workout schedule, but effects are reversible—the user can edit or delete the modified workout.
From the tool's definition Tool description states "Update an existing swimming workout in place (PUT)". The PUT HTTP method and "update" verb indicate data modification. The tool modifies an existing workout record reversibly.
Attacks that exploit this kind of access
Update an existing swimming workout in place (PUT). 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 update_swimming_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.
update_swimming_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 update_swimming_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 update_swimming_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.
update_swimming_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 →