Get an activity's description to check for existing coaching feedback.
AI agents call get_activity_description to retrieve information from MCPacer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (an activity's description) from Strava without creating, modifying, deleting, or executing operations. It is a read-only query consistent with other Read tools on the server like get_activities, get_activity_by_id, and get_activity_streams. The blast radius if misused is minimal—reading descriptions poses no risk to data integrity or user obligations.
From the tool's definition Tool name 'get_activity_description' and description 'Get an activity's description' indicate a retrieval operation with no modification or side effects. The stated purpose is to 'check for existing coaching feedback', which is a query operation.
Documented attack patterns abuse exactly the kind of access get_activity_description gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPacer, and nothing reaches the server without passing your rules. This is the rule we recommend for get_activity_description:
{
"version": "1",
"default": "deny",
"tools": {
"get_activity_description": {}
}
}get_activity_description is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get an activity's description to check for existing coaching feedback. It is categorised as a Read tool in the MCPacer MCP Server, which means it retrieves data without modifying state.
Register the MCPacer MCP server in PolicyLayer and add a rule for get_activity_description: 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 MCPacer. Nothing to install.
get_activity_description 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_activity_description 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_activity_description. 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_activity_description is provided by the MCPacer MCP server (wernerpe/mcpacer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPacer, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
32 MCPacer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.