Get wellness data including HRV, resting HR, sleep, and fatigue scores.
AI agents call get_wellness to retrieve information from Intervals Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves stored wellness statistics. It has no side effects, cannot modify or delete data, and poses minimal risk. The data retrieved (health metrics) is sensitive but access control and information sensitivity are separate from the functional risk category. Classification as Read is appropriate.
From the tool's definition Tool name 'get_wellness' and description 'Get wellness data' indicate data retrieval only. The tool queries existing wellness metrics (HRV, resting HR, sleep, fatigue scores) with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Get wellness data including HRV, resting HR, sleep, and fatigue scores. It is categorised as a Read tool in the Intervals Mcp MCP Server, which means it retrieves data without modifying state.
Register the Intervals 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 Mcp. 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 MCP server (ryansheppard/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 →