查询点位数据，支持按城市、状态、类型等条件筛选
AI agents call query_locations to retrieve information from POI 周边搜索 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters POI location data based on various criteria. It performs a database query operation with no side effects—data is not created, modified, or deleted. The filtering parameters indicate standard read-only search functionality. Misuse by an AI agent would have minimal blast radius (e.g., excessive queries or information disclosure of public location data).
From the tool's definition Tool description states '查询点位数据' (query POI data) with filtering by city, status, type—standard read operations.
Attacks that exploit this kind of access
查询点位数据，支持按城市、状态、类型等条件筛选. It is categorised as a Read tool in the POI 周边搜索 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the POI 周边搜索 MCP Server MCP server in PolicyLayer and add a rule for query_locations: 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 POI 周边搜索 MCP Server. Nothing to install.
query_locations 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 query_locations 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 query_locations. 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.
query_locations is provided by the POI 周边搜索 MCP Server MCP server (jarvisxiong2022-hue/mcp-servers). 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 →