AI agents call usg_whitelist_check to retrieve information from AF_MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query against a whitelist to verify if an IP meets security criteria. It retrieves or queries data (whitelist status) with no side effects—no creation, modification, deletion, or execution of external operations. It falls squarely into the Read category.
From the tool's definition Tool name 'usg_whitelist_check' and description indicate a check/validation operation ('执行...校验' = 'perform...check/validation'). The operation queries whitelist status against a specified IP without modifying any data or configuration.
Attacks that exploit this kind of access
对指定 IP 执行 USG 五层白名单校验。. It is categorised as a Read tool in the AF_MCP MCP Server, which means it retrieves data without modifying state.
Register the AF_ MCP server in PolicyLayer and add a rule for usg_whitelist_check: 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 AF_MCP. Nothing to install.
usg_whitelist_check 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 usg_whitelist_check 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 usg_whitelist_check. 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.
usg_whitelist_check is provided by the AF_ MCP server (xiaqijun/af_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 →