AI agents call get_interfaces 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 device interface metadata without performing any writes, deletions, or state changes. It is a standard informational query typical of network device management interfaces. The low severity reflects that interface information is generally non-sensitive configuration data needed for device diagnostics and monitoring.
From the tool's definition Tool name 'get_interfaces' and description state it queries interface information including status, IP addresses, and descriptions. The verb '查询' (query/retrieve) indicates data retrieval with no modification.
Attacks that exploit this kind of access
查询接口信息，包含接口状态、IP 地址、描述等。. 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_interfaces: 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_interfaces 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_interfaces 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_interfaces. 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_interfaces 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.
get_interfaces 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 →