AI agents call get_readiness_data to retrieve information from Oura MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries personal health metrics from the Oura API without modifying, deleting, or executing external operations. It retrieves existing data within a date range. Worst-case misuse would expose personal health information, but the tool itself has no destructive, financial, or code execution capability. Classified as Read with low severity due to limited blast radius of health data exposure alone.
From the tool's definition Tool name 'get_readiness_data' and description 'Get readiness data for a specific date range' indicate data retrieval with no modification. Sibling tools (get_resilience_data, get_sleep_data, get_today_*) all follow the same read-only pattern.
Documented attack patterns abuse exactly the kind of access get_readiness_data gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Oura MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_readiness_data:
{
"version": "1",
"default": "deny",
"tools": {
"get_readiness_data": {}
}
}get_readiness_data 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 readiness data for a specific date range. It is categorised as a Read tool in the Oura MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Oura MCP Server MCP server in PolicyLayer and add a rule for get_readiness_data: 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 Oura MCP Server. Nothing to install.
get_readiness_data 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_readiness_data 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_readiness_data. 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_readiness_data is provided by the Oura MCP Server MCP server (tomekkorbak/oura-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Oura MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Oura MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.