AI agents call block_list_exceptions 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 queries existing exception blocking configurations. It performs a read-only lookup of security device settings without creating, modifying, deleting, or executing any operations. The verb '查询' (query/check) confirms the read-only nature. Despite the security context, the tool has no ability to change system state, making it a Read category with low severity and blast radius.
From the tool's definition Tool name 'block_list_exceptions' and description '查询例外封锁配置列表' (Query exception blocking configuration list) indicates a query/retrieval operation with no modification capability.
Attacks that exploit this kind of access
查询例外封锁配置列表。. 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_exceptions: 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_exceptions 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_exceptions 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_exceptions. 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_exceptions 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.
block_list_exceptions is one line of AF_'s registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →