AI agents invoke local_traceroute to trigger actions in Net. 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.
Traceroute is a network diagnostic tool that executes an OS-level command to send packets and measure routes to a destination. Despite the empty description (which lowers confidence), the name strongly implies executing a local system command. This falls under Execute as it triggers an external operation. Misuse could be used to probe internal network topology, but blast radius is generally medium.
From the tool's definition Tool name 'local_traceroute' implies execution of a local network diagnostic command (traceroute), which runs a system-level process to probe network paths.
Attacks that exploit this kind of access
local_traceroute. It is categorised as a Execute tool in the Net MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Net MCP server in PolicyLayer and add a rule for local_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 Net. Nothing to install.
local_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 local_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 local_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.
local_traceroute is provided by the Net MCP server (steelcutoatmeal/net-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 →