AI agents call get_nfregex_metrics 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 operational metrics from the nfregex firewall module in a read-only manner. It queries existing metric data (blocked_packets count, active status) without modifying, deleting, or executing any operations. The Prometheus format confirms it is a metrics export endpoint. There is no capability to alter system state, delete data, or trigger external operations.
From the tool's definition Tool name 'get_nfregex_metrics' and description 'Prometheus-format metrics for the nfregex module (blocked_packets, active)' indicate retrieval of monitoring data with no side effects.
Attacks that exploit this kind of access
Prometheus-format metrics for the nfregex module (blocked_packets, active). 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 get_nfregex_metrics: 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.
get_nfregex_metrics 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_nfregex_metrics 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_nfregex_metrics. 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_nfregex_metrics 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 →