AI agents use rename_phj_service 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 configuration data (a porthijack service rule name) without deleting it, making it Write rather than Destructive. However, severity is elevated to 'high' because misconfiguration of firewall/proxy rules could impact network security posture, traffic routing, or security policy enforcement.
From the tool's definition Tool description states it 'Rename a porthijack rule' — this modifies an existing rule/configuration in what appears to be a firewall/proxy system. The action is reversible (a rule can be renamed back), but affects active security infrastructure.
Attacks that exploit this kind of access
Rename a porthijack rule. 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 rename_phj_service: 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.
rename_phj_service 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 rename_phj_service 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 rename_phj_service. 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.
rename_phj_service 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 →