AI agents call place_details to retrieve information from Google Maps Platform 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 description is empty, the name 'place_details' and the context of sibling read-only tools on a Google Maps service strongly indicate this fetches details about a place without modifying data. No side effects are evident. Confidence is slightly reduced due to the missing description, but the naming and server context make Read the clear classification.
From the tool's definition Tool name is 'place_details' which by convention retrieves information about a place. Server description states it 'Provides MCP tools for Google Maps services' focused on 'directions, geocoding, distance matrix, and places search' — all read-only operations.
Documented attack patterns abuse exactly the kind of access place_details gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Maps Platform MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for place_details:
{
"version": "1",
"default": "deny",
"tools": {
"place_details": {}
}
}place_details 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.
place_details. It is categorised as a Read tool in the Google Maps Platform MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Maps Platform MCP Server MCP server in PolicyLayer and add a rule for place_details: 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 Google Maps Platform MCP Server. Nothing to install.
place_details 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 place_details 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 place_details. 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.
place_details is provided by the Google Maps Platform MCP Server MCP server (neutrollized/google-maps-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Maps Platform 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.
6 Google Maps Platform MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.