List activity summaries for a date range. Returns ONLY compact identification data (id, date, name, type, distance, moving_time, elevation, heart rate, speed, training load, fitness/fatigue, calories, source). To analyze an activity in depth, you MUST call get_activity — it returns 100+ fields in...
AI agents call list_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 queries activity data without side effects. It returns summary-level information (id, date, name, type, distance, etc.) and explicitly directs users to call get_activity for deeper analysis. There is no capability to create, modify, delete, or execute operations. The blast radius of misuse is minimal — an agent could only access activity history data that has already been recorded.
From the tool's definition Tool description states it 'List activity summaries' and 'Returns ONLY compact identification data' — explicitly read-only retrieval of summarized activity information with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
List activity summaries for a date range. Returns ONLY compact identification data (id, date, name, type, distance, moving_time, elevation, heart rate, speed, training load, fitness/fatigue, calories, source). To analyze an activity in depth, you MUST call get_activity — it returns 100+ fields including power, cadence, zones, weather, performance metrics, intervals, and more. 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 list_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.
list_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 list_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 list_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.
list_activities is provided by the Intervals Icu MCP Server MCP server (moxus/intervals-icu-mcp-ts). 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 →