AI agents call pfsense_get_routing_gateway to retrieve information from Pfsense without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that queries gateway routing configuration from pfSense. While severity is elevated to medium because gateway information could be used to understand firewall topology and routing paths (useful for planning attacks), the tool itself performs no modifications or destructive actions. The blast radius is contained to information disclosure risk rather than direct system compromise.
From the tool's definition Tool name contains 'get' and description shows a GET HTTP method to a read-only endpoint (/api/v2/routing/gateway). The action retrieves gateway routing information without modifying state.
Attacks that exploit this kind of access
GET /api/v2/routing/gateway. It is categorised as a Read tool in the Pfsense MCP Server, which means it retrieves data without modifying state.
Register the Pfsense MCP server in PolicyLayer and add a rule for pfsense_get_routing_gateway: 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 Pfsense. Nothing to install.
pfsense_get_routing_gateway 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 pfsense_get_routing_gateway 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 pfsense_get_routing_gateway. 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.
pfsense_get_routing_gateway is provided by the Pfsense MCP server (abl030/pfsense-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 →