使用 Google Places API 搜索地点
AI agents call maps_search_places to retrieve information from Google Maps MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the Google Places API to retrieve place information based on search criteria. It returns data about locations without creating, modifying, deleting, or executing any operations. The sibling tools (directions, distance_matrix, elevation, geocode, place_details, reverse_geocode) are all read-only queries.
From the tool's definition Tool performs 'search' operation on Google Places API to find place information. The description states it 'searches places' (搜索地点), which is a retrieval operation with no modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
使用 Google Places API 搜索地点. It is categorised as a Read tool in the Google Maps MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Maps MCP Server MCP server in PolicyLayer and add a rule for maps_search_places: 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 MCP Server. Nothing to install.
maps_search_places 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 maps_search_places 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 maps_search_places. 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.
maps_search_places is provided by the Google Maps MCP Server MCP server (lesonky/google-maps-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 →