AI agents call local_routes to retrieve information from Net 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 the current local routing table—a passive diagnostic operation with no side effects, no data modification, and no execution of commands or scripts. It falls squarely into the Read category. Severity is low because exposure of routing table information, while potentially useful for reconnaissance, does not enable direct system compromise or data destruction on its own.
From the tool's definition Tool name 'local_routes' and description 'Show the local routing table' indicate a query/retrieval operation with no modification of data. The verb 'show' denotes read-only access to existing routing configuration.
Attacks that exploit this kind of access
Show the local routing table. It is categorised as a Read tool in the Net MCP Server, which means it retrieves data without modifying state.
Register the Net MCP server in PolicyLayer and add a rule for local_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 Net. Nothing to install.
local_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 local_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 local_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.
local_routes 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 →