upload_workout
AI agents use upload_workout to create or update resources in Garmin MCP Server for Poke — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Garmin MCP Server for Poke environment.
Upload operations create or modify records reversibly—users can edit or remove uploaded workouts later. This is characteristic of Write category. Severity is medium because unauthorized workout uploads could pollute a user's fitness data and potentially trigger unwanted notifications or training plan adjustments, but the impact is limited to that user's account and is reversible.
From the tool's definition Tool name 'upload_workout' indicates a create/modify operation that adds or updates workout data in the Garmin Connect system.
Attacks that exploit this kind of access
upload_workout. It is categorised as a Write tool in the Garmin MCP Server for Poke MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Garmin MCP Server for Poke MCP server in PolicyLayer and add a rule for upload_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 MCP Server for Poke. Nothing to install.
upload_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 upload_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 upload_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.
upload_workout is provided by the Garmin MCP Server for Poke MCP server (theol0403/garmin-mcp-poke). 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 →