get_progress_summary
AI agents call get_progress_summary 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 a summary of user training progress from Garmin Connect—a read-only operation with no side effects. Misuse by an AI agent would only expose personal fitness data already accessible to the authorized user, posing minimal risk. The empty description and naming consistency with other safe getter methods support Read classification with high confidence.
From the tool's definition Tool name 'get_progress_summary' with 'get_' prefix indicates data retrieval. All sibling tools on this server (get_activities, get_fitness, get_goals, etc.) are read-only queries of Garmin Connect metrics.
Attacks that exploit this kind of access
get_progress_summary. 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_progress_summary: 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_progress_summary 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_progress_summary 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_progress_summary. 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_progress_summary 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 →