Aggregate a health metric by day, week, or month.
AI agents call summary to retrieve information from Apple Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and aggregates existing health data from the local SQLite database without modifying, deleting, or executing external operations. Aggregation is a read operation that transforms data for presentation but does not alter the underlying dataset.
From the tool's definition Tool 'summary' aggregates health metrics by time period. The description indicates data retrieval and aggregation (computing summaries from existing data) with no mention of modification, deletion, or external execution.
Attacks that exploit this kind of access
Aggregate a health metric by day, week, or month. It is categorised as a Read tool in the Apple Health MCP Server, which means it retrieves data without modifying state.
Register the Apple Health MCP server in PolicyLayer and add a rule for summary: 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. Nothing to install.
summary 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 summary 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 summary. 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.
summary is provided by the Apple Health MCP server (smarzola/apple-health-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 →