AI agents invoke tunnel_restart to trigger actions in LocalAnt. 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 triggers an external operation that restarts a public tunnel service. While not destructive (the tunnel can be restarted again), it executes a command with side effects that could disrupt active connections or services relying on that tunnel. The effect is not a simple read or write of data, but an active system operation.
From the tool's definition Tool name 'tunnel_restart' and description 'Restart the public tunnel' indicate invocation of an external operation (tunnel service restart) whose effects are not immediately reversible and depend on system state.
Attacks that exploit this kind of access
Restart the public tunnel. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for tunnel_restart: 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 LocalAnt. Nothing to install.
tunnel_restart 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 tunnel_restart 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 tunnel_restart. 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.
tunnel_restart is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →