get_training_plans_list
AI agents call get_training_plans_list to retrieve information from Claude Garmin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists training plans from Garmin Connect without modifying, deleting, or executing external operations. The naming convention and server context strongly suggest it queries and returns plan data. No side effects are indicated. Low severity because accessing training plan metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_training_plans_list' with 'get' prefix and '_list' suffix indicates data retrieval. All sibling tools are getters (get_activities, get_fitness, get_goals, etc.), confirming a pattern of read-only queries.
Attacks that exploit this kind of access
get_training_plans_list. It is categorised as a Read tool in the Claude Garmin MCP Server, which means it retrieves data without modifying state.
Register the Claude Garmin MCP server in PolicyLayer and add a rule for get_training_plans_list: 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 Claude Garmin. Nothing to install.
get_training_plans_list 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_training_plans_list 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_training_plans_list. 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_training_plans_list is provided by the Claude Garmin MCP server (jack-abyss/claude-garmin). 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 →