AI agents call block_list_attackers 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 or lists data about blocked/attacker IPs without modifying, deleting, or executing operations. It fits the Read category as a query operation. Severity is medium because exposure of attacker IP lists could inform threat actors about detection and enable evasion, but the tool itself performs no destructive or dangerous operations.
From the tool's definition Tool name 'block_list_attackers' and description '查询封锁攻击者 IP 列表' (query blocked attacker IP list) indicate a retrieval/query operation with no side effects. The verb '查询' (query/retrieve) confirms read-only semantics.
Attacks that exploit this kind of access
查询封锁攻击者 IP 列表。. 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 block_list_attackers: 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.
block_list_attackers 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 block_list_attackers 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 block_list_attackers. 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.
block_list_attackers 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 →