AI agents call export-route-tcx 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 reads/retrieves a route from Strava and exports it to a local file. While it writes a file locally, the primary action is fetching/reading data from Strava and saving to a pre-configured directory (not user-controlled path), making it primarily a Read operation with minimal risk.
From the tool's definition Exports a specific Strava route in TCX format and saves it to a pre-configured local directory
Attacks that exploit this kind of access
Exports a specific Strava route in TCX format and saves it to a pre-configured local directory. 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 export-route-tcx: 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.
export-route-tcx 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 export-route-tcx 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 export-route-tcx. 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.
export-route-tcx 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.