AI agents use change_phj_destination to create or update resources in Firegex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Firegex environment.
This tool modifies an existing network firewall/proxy rule by changing its destination IP and port. It is a reversible configuration change (Write), but carries high severity because misconfiguring network routing rules could redirect traffic to attacker-controlled destinations, exposing sensitive communications or bypassing security controls.
From the tool's definition Repoint an existing porthijack rule to a new ip_dst:proxy_port
Attacks that exploit this kind of access
Repoint an existing porthijack rule to a new ip_dst:proxy_port. It is categorised as a Write tool in the Firegex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Firegex MCP server in PolicyLayer and add a rule for change_phj_destination: 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 Firegex. Nothing to install.
change_phj_destination 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 change_phj_destination 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 change_phj_destination. 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.
change_phj_destination is provided by the Firegex MCP server (umbra2728/firegex-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 →