Read raw Health samples across one or more dates, filtered by type_keys/tags/kinds, with manifest-aware pagination.
AI agents call health.read_samples to retrieve information from Nucleus Apple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves health data from Apple's Health framework without creating, modifying, deleting, or executing operations. However, severity is elevated to 'medium' rather than 'low' because health data is sensitive personal information (medical/fitness records); unauthorized access or over-sharing by an AI agent could pose privacy and safety risks, though the tool itself performs only retrieval.
From the tool's definition Tool name explicitly includes 'read' and description states 'Read raw Health samples' — a data retrieval operation with no modification or deletion. The filtering and pagination are query parameters, not side effects.
Documented attack patterns abuse exactly the kind of access health.read_samples gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nucleus Apple, and nothing reaches the server without passing your rules. This is the rule we recommend for health.read_samples:
{
"version": "1",
"default": "deny",
"tools": {
"health.read_samples": {}
}
}health.read_samples 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.
Read raw Health samples across one or more dates, filtered by type_keys/tags/kinds, with manifest-aware pagination. It is categorised as a Read tool in the Nucleus Apple MCP Server, which means it retrieves data without modifying state.
Register the Nucleus Apple MCP server in PolicyLayer and add a rule for health.read_samples: 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 Nucleus Apple. Nothing to install.
health.read_samples 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 health.read_samples 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 health.read_samples. 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.
health.read_samples is provided by the Nucleus Apple MCP server (zish-rob-crur/nucleus-apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nucleus Apple, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Nucleus Apple tools catalogued and risk-classified — across an index of 43,000+ MCP servers.