AI agents call block_list_business 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.
The tool performs a query/retrieval operation ('查询' means query) on IP blocklist data. It has no side effects, does not execute code, does not modify data, and does not delete or create anything. This is a straightforward read operation with minimal blast radius if misused—an agent could only over-query or access information about blocked IPs, which does not cause system damage.
From the tool's definition Tool name 'block_list_business' and description '查询业务封锁 IP 列表' (query business blocked IP list) indicates a read-only operation that retrieves or queries data about blocked IPs without modifying or deleting anything.
Attacks that exploit this kind of access
查询业务封锁 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_business: 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_business 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_business 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_business. 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_business 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 →