search_activities_tool
AI agents call search_activities_tool to retrieve information from Strava MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to search or filter Strava activities, which is a read-only data retrieval operation with no capability to modify, execute, or delete data. No side effects are expected from searching activity data. Confidence is slightly reduced (0.85 vs 1.0) because the tool description is empty, but contextual evidence from server purpose and sibling tools is strong.
From the tool's definition Tool name 'search_activities_tool' indicates a query/retrieval operation. Server description states tools 'retrieve athlete statistics and activity data' and 'listing recent activities'.
Attacks that exploit this kind of access
search_activities_tool. It is categorised as a Read tool in the Strava MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Strava MCP Server MCP server in PolicyLayer and add a rule for search_activities_tool: 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 MCP Server. Nothing to install.
search_activities_tool 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 search_activities_tool 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 search_activities_tool. 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.
search_activities_tool is provided by the Strava MCP Server MCP server (saxenanurag/strava-mcp). 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 →