AI agents call get-recent-activities 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 queries and returns data (recent activities) for an authenticated user without modifying, deleting, or executing external operations. It is a straightforward data retrieval operation typical of Read category tools. The low severity reflects that the worst outcome of misuse would be unauthorized access to activity history, which is concerning but not destructive or financial.
From the tool's definition Tool name is 'get-recent-activities' and description states it 'Fetches the most recent activities' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Fetches the most recent activities for 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-recent-activities: 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-recent-activities 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-recent-activities 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-recent-activities. 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-recent-activities 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.