View active connections (READ-ONLY, safe)
AI agents call mikrotik_get_connection_tracking to retrieve information from MikroTik Cursor MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves network connection tracking data without modifying, executing code, or deleting anything. The READ-ONLY designation and passive nature (viewing/querying) clearly places it in the Read category. Low severity because connection metadata viewing has minimal blast radius—it cannot alter network configuration or access sensitive credentials directly.
From the tool's definition Tool name contains 'get' and description explicitly states 'READ-ONLY, safe' with focus on 'View active connections'
Attacks that exploit this kind of access
View active connections (READ-ONLY, safe). It is categorised as a Read tool in the MikroTik Cursor MCP MCP Server, which means it retrieves data without modifying state.
Register the MikroTik Cursor MCP server in PolicyLayer and add a rule for mikrotik_get_connection_tracking: 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_get_connection_tracking 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 mikrotik_get_connection_tracking 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_get_connection_tracking. 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_get_connection_tracking 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 →