save_plan · Garmin MCP: Risk & Policy

WHAT IT DOES

What save_plan does on Garmin

AI agents use save_plan 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.

WHY IT NEEDS A POLICY

Why save_plan needs a policy

The name 'save_plan' strongly suggests persisting or modifying a plan (reversible operation), placing it in the Write category. The lack of description limits confidence slightly, but the context of sibling tools and the naming pattern confirms this is not a Read (no 'get'), Destructive (no 'delete'), Execute (no command execution indicated), or Financial operation.

From the tool's definition Tool name 'save_plan' indicates a create or modify action typical of Write operations. No description provided, but in context of a workout/health management server alongside 'create_running_workout', 'create_strength_workout', and other creation/modification…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

save_plan Rate-limited

save_plan 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "save_plan": {
      "limits": [
        {
          "counter": "save_plan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Garmin, so you can run agents against it safely.

FAQ

Questions about save_plan

What does the save_plan tool do? +

save_plan. 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.

How do I enforce a policy on save_plan? +

Register the Garmin MCP server in PolicyLayer and add a rule for save_plan: 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.

What risk level is save_plan? +

save_plan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit save_plan? +

Yes. Add a rate_limit block to the save_plan 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.

How do I block save_plan completely? +

Set action: deny in the PolicyLayer policy for save_plan. 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.

What MCP server provides save_plan? +

save_plan is provided by the Garmin MCP server (marcelohensantos/garmin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.