List IP routing table entries.
AI agents call ip_routes to retrieve information from RouterOS MCP Server 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 routing table entries from a RouterOS device. It performs no modifications, deletions, or command execution—only data querying. The blast radius of misuse is minimal since viewing routing tables does not alter network configuration or trigger actions. It falls clearly under the Read category.
From the tool's definition Tool name 'ip_routes' and description 'List IP routing table entries' indicate a read-only query operation that retrieves routing configuration data without modification.
Attacks that exploit this kind of access
List IP routing table entries. It is categorised as a Read tool in the RouterOS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RouterOS MCP Server MCP server in PolicyLayer and add a rule for ip_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 RouterOS MCP Server. Nothing to install.
ip_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 ip_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 ip_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.
ip_routes is provided by the RouterOS MCP Server MCP server (sevaepsteyn/routeros_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 →