AI agents call get_whitelist_config 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 returns whitelist configuration and statistics. It performs a read-only query operation with no side effects, no code execution, no data modification, and no destructive actions. The function is informational in nature, supporting monitoring and auditing of existing security policies.
From the tool's definition Tool name 'get_whitelist_config' with description '返回当前有效的白名单文件配置与规则统计' (returns current active whitelist file configuration and rule statistics). The verb 'get' and 'return' indicate data retrieval without modification or execution.
Attacks that exploit this kind of access
返回当前有效的白名单文件配置与规则统计。. 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_config: 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_config 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_config 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_config. 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_config 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 →