Execute SQL queries on Apple Health data. Supports SELECT queries only.
AI agents call health_query to retrieve information from Apple Health MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool executes SQL (which could nominally fall under Execute category), the explicit limitation to SELECT queries means it retrieves and queries data without side effects. Health data is sensitive personal information; unauthorized read access poses high severity due to privacy implications and potential for misuse (e.g., learning about medical conditions, treatments, medications).
From the tool's definition Tool description explicitly states 'Execute SQL queries on Apple Health data. Supports SELECT queries only.' The restriction to SELECT-only queries confirms this is read-only access without write, delete, or destructive capabilities.
Documented attack patterns abuse exactly the kind of access health_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Health MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for health_query:
{
"version": "1",
"default": "deny",
"tools": {
"health_query": {}
}
}health_query 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.
Execute SQL queries on Apple Health data. Supports SELECT queries only. It is categorised as a Read tool in the Apple Health MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Apple Health MCP Server MCP server in PolicyLayer and add a rule for health_query: 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 Apple Health MCP Server. Nothing to install.
health_query 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_query 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_query. 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_query is provided by the Apple Health MCP Server MCP server (neiltron/apple-health-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Health MCP Server, 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.
3 Apple Health MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.