AI agents call list_phj_services to retrieve information from Firegex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing port-hijack service configurations. It performs no side effects, does not execute or modify firewall rules, and does not delete or create data. It is a pure read operation that enumerates current system state, making it the lowest risk category.
From the tool's definition Tool name 'list_phj_services' and description 'List port-hijack rules' indicate a query/retrieval operation with no modification or execution of rules.
Attacks that exploit this kind of access
List port-hijack rules (each redirects public_port → proxy_port on ip_dst). It is categorised as a Read tool in the Firegex MCP Server, which means it retrieves data without modifying state.
Register the Firegex MCP server in PolicyLayer and add a rule for list_phj_services: 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.
list_phj_services 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 list_phj_services 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 list_phj_services. 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.
list_phj_services 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 →