AI agents call get_whitelist_rules 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 retrieves and queries security whitelist configuration data without creating, modifying, or deleting any rules. It is informational and read-only in nature. Severity is medium (not low) because the whitelist data it returns could reveal security policy details that inform an attacker about which entities are trusted, potentially enabling bypass strategies or reconnaissance.
From the tool's definition Tool name 'get_whitelist_rules' and description 'returns the complete rule configuration of the currently active whitelist file' indicate data retrieval with no modification.
Attacks that exploit this kind of access
返回当前生效白名单文件的完整规则配置。. 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 get_whitelist_rules: 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.
get_whitelist_rules 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_whitelist_rules 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_whitelist_rules. 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_whitelist_rules 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 →