get_wellness
AI agents call get_wellness 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.
The tool follows the 'get_*' naming pattern indicating data retrieval with no side effects. The server description explicitly states it enables fetching and filtering health metrics. Wellness data retrieval has minimal blast radius—it only reads personal fitness/health information without modifying, deleting, or executing operations.
From the tool's definition Tool name is 'get_wellness' with no description provided. Based on sibling tools (get_activities, get_grouped_activities, get_grouped_wellness) and server purpose of 'fetch, filter, and group activities or health metrics', this tool retrieves wellness data.
Attacks that exploit this kind of access
get_wellness. 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_wellness: 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_wellness 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_wellness 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_wellness. 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_wellness 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 →