AI agents call get-athlete-shoes to retrieve information from Strava without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves athlete profile data (shoes in this context) for the authenticated user. It performs no data modification, deletion, or external execution. The blast radius is minimal—an agent calling this tool gains read-only visibility into personal fitness equipment metadata. Classification as Read is appropriate.
From the tool's definition Tool name is 'get-athlete-shoes' and description states 'Fetches the authenticated athlete' — both indicate a retrieval operation with no side effects. The verb 'Fetches' confirms query-only semantics.
Attacks that exploit this kind of access
Fetches the authenticated athlete. It is categorised as a Read tool in the Strava MCP Server, which means it retrieves data without modifying state.
Register the Strava MCP server in PolicyLayer and add a rule for get-athlete-shoes: 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 Strava. Nothing to install.
get-athlete-shoes 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-athlete-shoes 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-athlete-shoes. 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-athlete-shoes is provided by the Strava MCP server (@r-huijts/strava-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.