Look up one Google place by Place ID. Returns hours, delivery/dine-in flags, and other detail fields. Set includeAtmosphere=true to also fetch editorialSummary and reviews (higher pricing tier).
AI agents call places_detail to retrieve information from DOL WHD MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves/queries data about a place from Google Places API. It has no side effects, does not modify any data, and simply fetches details like hours and flags. Severity is low as it only reads publicly available place information.
From the tool's definition Look up one Google place by Place ID. Returns hours, delivery/dine-in flags, and other detail fields.
Attacks that exploit this kind of access
Look up one Google place by Place ID. Returns hours, delivery/dine-in flags, and other detail fields. Set includeAtmosphere=true to also fetch editorialSummary and reviews (higher pricing tier). It is categorised as a Read tool in the DOL WHD MCP MCP Server, which means it retrieves data without modifying state.
Register the DOL WHD MCP server in PolicyLayer and add a rule for places_detail: 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 DOL WHD MCP. Nothing to install.
places_detail 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 places_detail 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 places_detail. 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.
places_detail is provided by the DOL WHD MCP server (uhq-actual/dol_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 →