清空通过聊天保存的 USG 连接账号，后续需重新调用 set_usg_connection。
AI agents call clear_usg_connection to permanently remove resources in AF_MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly clears/purges the stored USG connection credentials, requiring re-authentication afterward. This is a destructive action (data erasure) rather than a simple write, as the saved connection configuration is deleted and cannot be recovered without re-entering it manually.
From the tool's definition 清空通过聊天保存的 USG 连接账号 (Clear/purge the USG connection account saved via chat)
Attacks that exploit this kind of access
清空通过聊天保存的 USG 连接账号，后续需重新调用 set_usg_connection。. It is categorised as a Destructive tool in the AF_MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AF_ MCP server in PolicyLayer and add a rule for clear_usg_connection: 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.
clear_usg_connection is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_usg_connection 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 clear_usg_connection. 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.
clear_usg_connection 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 →