使用第三方服务获取公网IP地址。
AI agents call get_ip to retrieve information from Baidu Map Search 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 public IP address information from a third-party service. It is a read-only query operation that returns network information without modifying any data, executing commands, or triggering external operations. The blast radius is minimal—an agent obtaining a public IP address poses negligible security risk. Classified as Read with low severity.
From the tool's definition Tool name 'get_ip' and description '使用第三方服务获取公网IP地址' (uses third-party service to retrieve public IP address) indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
使用第三方服务获取公网IP地址。. It is categorised as a Read tool in the Baidu Map Search MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Baidu Map Search MCP Server MCP server in PolicyLayer and add a rule for get_ip: 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 Baidu Map Search MCP Server. Nothing to install.
get_ip 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 get_ip 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 get_ip. 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.
get_ip is provided by the Baidu Map Search MCP Server MCP server (leng-2024/agent-with-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 →