AI agents use usg_apply_blacklist_unblock 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 unblocks (removes from blacklist) entries on a security device, which is a reversible write operation that modifies firewall/security policy state. While it affects security posture, the action can be undone by re-blocking the entry. It requires explicit confirmation (confirmed=true flag) which provides some safeguard.
From the tool's definition Tool name 'usg_apply_blacklist_unblock' and description '按 action_id 实际执行 USG 黑名单解封,需 confirmed=true' (translates to: 'Actually execute USG blacklist unblocking by action_id, requires confirmed=true').
Attacks that exploit this kind of access
按 action_id 实际执行 USG 黑名单解封,需 confirmed=true。. 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 usg_apply_blacklist_unblock: 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_apply_blacklist_unblock 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 usg_apply_blacklist_unblock 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_apply_blacklist_unblock. 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_apply_blacklist_unblock 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 →