Advertise network via BGP
AI agents use mikrotik_add_bgp_network to create or update resources in MikroTik Cursor MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MikroTik Cursor MCP environment.
This tool creates a new BGP network advertisement entry on the MikroTik router. It modifies routing configuration by adding a network to be announced via BGP, which is a write operation. The blast radius is high because misconfiguring BGP advertisements can disrupt routing for many downstream networks, potentially causing widespread connectivity issues or route leaks.
From the tool's definition Advertise network via BGP
Attacks that exploit this kind of access
Advertise network via BGP. It is categorised as a Write tool in the MikroTik Cursor MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MikroTik Cursor MCP server in PolicyLayer and add a rule for mikrotik_add_bgp_network: 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 MikroTik Cursor MCP. Nothing to install.
mikrotik_add_bgp_network is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the mikrotik_add_bgp_network 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 mikrotik_add_bgp_network. 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.
mikrotik_add_bgp_network is provided by the MikroTik Cursor MCP server (kevinpez/mikrotik-cursor-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 →