AI agents use upload_course to create or update resources in Garmin MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Garmin MCP Server environment.
The 'upload_course' tool fits the Write category as it creates or modifies course data in the Garmin fitness ecosystem. It is not Destructive (no irreversible deletion indicated), not Execute (no code/command execution), and not Financial.
From the tool's definition Tool name 'upload_course' indicates creation/modification of course data in Garmin Connect. The sibling tools (add_body_composition, add_gear_to_activity, add_hydration_data, add_weigh_in, create_custom_food, create_strength_workout, create_walk_run_workout)…
Documented attack patterns abuse exactly the kind of access upload_course gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Garmin MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_course:
{
"version": "1",
"default": "deny",
"tools": {
"upload_course": {
"limits": [
{
"counter": "upload_course_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_course stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
upload_course. It is categorised as a Write tool in the Garmin MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Garmin MCP Server MCP server in PolicyLayer and add a rule for upload_course: 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. Nothing to install.
upload_course 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_course 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_course. 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_course is provided by the Garmin MCP Server MCP server (taxuspt/garmin_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 126 Garmin MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
126 Garmin MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.