AI agents call 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.
whitelist_check retrieves or queries whitelist status against a given IP. It performs no writes, modifications, deletions, or external operations—purely informational lookup. The description emphasizes it is read-only inspection for manual verification or agent self-checking. This is a classic Read operation with minimal blast radius if misused by an agent (worst case: unnecessary validation queries).
From the tool's definition Tool description explicitly states '仅查询，不修改任何状态' (query only, does not modify any state). The tool performs whitelist validation/checking of an IP address without side effects.
Attacks that exploit this kind of access
对给定 IP 做五层白名单校验（仅查询，不修改任何状态）。用于人工核对或研判智能体自检。. 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 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.
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 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 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.
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 →