AI agents call get_calendar to retrieve information from Garmin Workouts MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves calendar data with no apparent side effects. The server explicitly mentions viewing calendar data as part of its functionality. This is a read-only operation with minimal blast radius. Confidence is slightly reduced due to empty description, but the naming and context are clear.
From the tool's definition Tool name 'get_calendar' and server context describes 'viewing activities, calendar data' as a read operation. No description provided, but naming and sibling context strongly indicate data retrieval.
Documented attack patterns abuse exactly the kind of access get_calendar gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Garmin Workouts MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_calendar:
{
"version": "1",
"default": "deny",
"tools": {
"get_calendar": {}
}
}get_calendar 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_calendar. It is categorised as a Read tool in the Garmin Workouts MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Garmin Workouts MCP Server MCP server in PolicyLayer and add a rule for get_calendar: 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 Workouts MCP Server. Nothing to install.
get_calendar 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_calendar 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_calendar. 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_calendar is provided by the Garmin Workouts MCP Server MCP server (st3v/garmin-workouts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Garmin Workouts MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Garmin Workouts MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.