get_workout_library
AI agents call get_workout_library 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.
The 'get_' prefix and naming pattern match other read-only query tools on the server that retrieve Garmin Connect data. No side effects, modifications, executions, or deletions are indicated. This tool retrieves workout library data for analysis purposes, aligned with the server's purpose of enabling training analysis and personalized plans based on metrics.
From the tool's definition Tool name 'get_workout_library' uses 'get' verb, consistent with sibling tools (get_activities, get_fitness, get_goals) which are all read-only data retrieval operations. Description is empty, so confidence cannot be higher.
Attacks that exploit this kind of access
get_workout_library. 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_workout_library: 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_workout_library 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_library 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_library. 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_library 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 →