get_grouped_activities
AI agents call get_grouped_activities to retrieve information from Intervals Icu MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and groups activity data from a fitness tracking platform. There is no indication it modifies, deletes, or executes external operations—it is a query operation that returns organized data summaries. The blast radius of misuse is minimal (unauthorized access to user fitness data), making severity low.
From the tool's definition Tool name 'get_grouped_activities' and server description indicating it 'fetch[es]' and provides 'structured summaries of workouts' with 'no side effects' mentioned.
Attacks that exploit this kind of access
get_grouped_activities. It is categorised as a Read tool in the Intervals Icu MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Intervals Icu MCP Server MCP server in PolicyLayer and add a rule for get_grouped_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 Intervals Icu MCP Server. Nothing to install.
get_grouped_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_grouped_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_grouped_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_grouped_activities is provided by the Intervals Icu MCP Server MCP server (vsidhart/intervals-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 →