Execute the traceroute command from the device to the specified destination.
AI agents invoke traceroute to trigger actions in Nornir MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a network diagnostic command (traceroute) on network devices. Although traceroute is non-destructive and read-only in intent, it is classified as Execute because it runs arbitrary commands on devices whose effects depend on arguments (destination parameter). An agent could misuse this to probe networks, map infrastructure, or probe unintended targets.
From the tool's definition Tool name is 'traceroute' and description states 'Execute the traceroute command from the device to the specified destination.' The verb 'Execute' and explicit reference to running a 'command' clearly indicate this is command execution.
Documented attack patterns abuse exactly the kind of access traceroute gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nornir MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for traceroute:
{
"version": "1",
"default": "deny",
"tools": {
"traceroute": {
"limits": [
{
"counter": "traceroute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}traceroute stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute the traceroute command from the device to the specified destination. It is categorised as a Execute tool in the Nornir MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nornir MCP Server MCP server in PolicyLayer and add a rule for traceroute: 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 Nornir MCP Server. Nothing to install.
traceroute is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the traceroute 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 traceroute. 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.
traceroute is provided by the Nornir MCP Server MCP server (yhvh-chen/nornir_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nornir MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Nornir MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.