List all distinct workout activity types and their counts.
AI agents call list_workout_types 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 retrieves and aggregates existing health data from a local SQLite database without creating, modifying, or deleting any information. It poses minimal security risk as it only exposes summary information about workout types already accessible in the user's own Apple Health export data.
From the tool's definition Tool name 'list_workout_types' and description 'List all distinct workout activity types and their counts' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all distinct workout activity types and their counts. 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 list_workout_types: 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.
list_workout_types 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 list_workout_types 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 list_workout_types. 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.
list_workout_types 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 →