AI agents use set_whitelist_file to create or update resources in AF_MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AF_MCP environment.
This tool creates or modifies whitelist configuration data in a reversible manner (the whitelist file path and settings can be changed or restored). It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). While it affects security device behavior through whitelist management, the tool itself performs configuration modification (Write).
From the tool's definition Tool description states '设置当前全局白名单文件路径,并持久化到本地配置文件' (set current global whitelist file path and persist to local configuration file). This modifies whitelist configuration and persists changes to disk.
Attacks that exploit this kind of access
设置当前全局白名单文件路径,并持久化到本地配置文件。. It is categorised as a Write tool in the AF_MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AF_ MCP server in PolicyLayer and add a rule for set_whitelist_file: 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.
set_whitelist_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_whitelist_file 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 set_whitelist_file. 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.
set_whitelist_file 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 →