AI agents use create_strength_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.
The tool name 'create_strength_workout' explicitly indicates data creation, making it a Write operation. Creating a workout record is reversible (can be deleted/modified later), so it does not rise to Destructive. The severity is medium because incorrect workout creation could clutter a user's fitness data and potentially mislead health tracking, but it is not irreversible or critically harmful.
From the tool's definition Tool name 'create_strength_workout' indicates it creates a new workout record. The server description states tools are 'read-only' and lists only 'get_*' tools; this 'create_*' tool contradicts that pattern and implies write capability.
Attacks that exploit this kind of access
create_strength_workout. 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 create_strength_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.
create_strength_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 create_strength_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 create_strength_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.
create_strength_workout 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 →