AI agents call get_acl_rules 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 performs a lookup/query of existing ACL rules on a security device. It has no side effects—it does not create, modify, delete, or execute actions. The 'get_' prefix and verb '查询' (query) confirm it is a retrieval operation. Misuse by an AI agent would be limited to unauthorized information disclosure of access control rules, a moderate information security concern but not operationally dangerous.
From the tool's definition Tool name 'get_acl_rules' and description '查询 ACL 列表及规则' (Query ACL list and rules) indicate a read-only query operation that retrieves access control list information without modifying any data.
Attacks that exploit this kind of access
查询 ACL 列表及规则。. 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 get_acl_rules: 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.
get_acl_rules 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 get_acl_rules 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 get_acl_rules. 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.
get_acl_rules 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 →