AI agents call preview_blacklist_unblock 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 displays information about a blacklist unblock action for review purposes. It performs no state changes, no destructive operations, and no side effects—it only queries and returns data about an existing action identified by action_id. This is a classic Read operation. The severity is low because previewing past actions poses minimal risk even if misused.
From the tool's definition Tool name 'preview_blacklist_unblock' and description '预览解封某一次封禁动作（按 action_id）' (Preview unblock action by action_id) indicates a preview/retrieval operation that examines a past blocking action without modifying it.
Attacks that exploit this kind of access
预览解封某一次封禁动作（按 action_id）。. 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 preview_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.
preview_blacklist_unblock 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 preview_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 preview_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.
preview_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 →