Run 'get router info routing-table all' on the Fortigate and return the routing table.
AI agents call fortigate_get_routes to retrieve information from Fortigate MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a diagnostic read operation to retrieve firewall routing information. It has no side effects and cannot modify system state or configuration. Even if misused by an AI agent, it would only expose network routing details without enabling any destructive or harmful actions. The minimal blast radius and read-only nature justify a 'low' severity classification.
From the tool's definition Tool description states 'get router info routing-table all' which is a read-only query operation that retrieves the routing table configuration from the Fortigate firewall.
Attacks that exploit this kind of access
Run 'get router info routing-table all' on the Fortigate and return the routing table. It is categorised as a Read tool in the Fortigate MCP MCP Server, which means it retrieves data without modifying state.
Register the Fortigate MCP server in PolicyLayer and add a rule for fortigate_get_routes: 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 Fortigate MCP. Nothing to install.
fortigate_get_routes 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 fortigate_get_routes 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 fortigate_get_routes. 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.
fortigate_get_routes is provided by the Fortigate MCP server (picaresco/mcp-fortigate). 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 →