Search Google Places (New) Text Search for businesses in an area. Designed as a per-round retrieval primitive for the Restaurant Research Agent. Returns deduplicated results with googleMapsUrl for source-tracing. Auto-pages up to maxResults (Google caps at ~60 per query). Defaults to includedTypes=[
AI agents call places_search 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 retrieves and queries publicly available business information from Google Places. It has no side effects, does not create, modify, or delete data, and does not execute code or trigger external operations beyond a read-only API call. The capability to auto-page results and the mention of source-tracing reinforce that it is a retrieval primitive. Classification as Read is appropriate.
From the tool's definition Tool description states it 'Search[es] Google Places (New) Text Search for businesses in an area' and 'Returns deduplicated results with googleMapsUrl for source-tracing.' The verb is search/retrieval with no modification or execution of external systems…
Attacks that exploit this kind of access
Search Google Places (New) Text Search for businesses in an area. Designed as a per-round retrieval primitive for the Restaurant Research Agent. Returns deduplicated results with googleMapsUrl for source-tracing. Auto-pages up to maxResults (Google caps at ~60 per query). Defaults to includedTypes=[. 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_search: 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_search 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_search 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_search. 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_search 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 →