AI agents call get_workout to retrieve information from Garmin Connect without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves workout definition data based on an identifier. It performs no modifications, deletions, executions, or financial operations. It is a straightforward data query operation consistent with other read tools on the server like 'get_activities' and 'get_activity_details'. The blast radius of misuse is minimal—an AI agent requesting this tool would only retrieve existing data without causing harm.
From the tool's definition Tool name is 'get_workout' and description states 'Get a specific workout definition by ID' - this is a retrieval operation with no side effects. The verb 'Get' and the action of fetching a definition by ID indicate a read-only query.
Documented attack patterns abuse exactly the kind of access get_workout gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Garmin Connect, and nothing reaches the server without passing your rules. This is the rule we recommend for get_workout:
{
"version": "1",
"default": "deny",
"tools": {
"get_workout": {}
}
}get_workout is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a specific workout definition by ID. It is categorised as a Read tool in the Garmin Connect MCP Server, which means it retrieves data without modifying state.
Register the Garmin Connect MCP server in PolicyLayer and add a rule for get_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 Connect. Nothing to install.
get_workout is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_workout is provided by the Garmin Connect MCP server (nicolasvegam/garmin-connect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 97 Garmin Connect tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
97 Garmin Connect tools catalogued and risk-classified — across an index of 42,500+ MCP servers.