AI agents use apply_nat_rule to create or update resources in AF_MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AF_MCP environment.
This tool modifies network routing/translation rules (NAT configuration) on security devices. While changes are theoretically reversible (can be undone by removing/updating the rule), the blast radius is high because incorrect NAT rules can disrupt network traffic, redirect traffic to attackers, or bypass security policies.
From the tool's definition Tool description: '提交 NAT 规则变更' (submit NAT rule changes). Performs network address translation rule modifications that are reversible. Requires prior preview_nat_rule call and confirmed=True flag, indicating a write operation with confirmation mechanism.
Attacks that exploit this kind of access
提交 NAT 规则变更。需先调用 preview_nat_rule,确认后以 confirmed=True 调用。. It is categorised as a Write tool in the AF_MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AF_ MCP server in PolicyLayer and add a rule for apply_nat_rule: 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.
apply_nat_rule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_nat_rule 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 apply_nat_rule. 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.
apply_nat_rule 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 →