tor_new_identity · Tor MCP: Risk & Policy

WHAT IT DOES

What tor_new_identity does on Tor

AI agents invoke tor_new_identity to trigger actions in Tor. 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.

WHY IT NEEDS A POLICY

Why tor_new_identity needs a policy

Creating a new Tor identity is an action that triggers an external operation (Tor network circuit rotation) whose effects depend on timing and network state. This is Execute rather than Read because it actively modifies the user's network state and anonymity configuration. It is not Destructive (reversible), Write (not data modification), or Financial.

From the tool's definition Tool named 'tor_new_identity' with empty description; sibling tools indicate Tor network control (tor_check_anonymity, tor_privacy_status, tor_private_fetch); 'new_identity' typically means requesting a new Tor circuit/exit node

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tor_new_identity Rate-limited

tor_new_identity 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "tor_new_identity": {
      "limits": [
        {
          "counter": "tor_new_identity_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tor, so you can run agents against it safely.

FAQ

Questions about tor_new_identity

What does the tor_new_identity tool do? +

tor_new_identity. It is categorised as a Execute tool in the Tor MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tor_new_identity? +

Register the Tor MCP server in PolicyLayer and add a rule for tor_new_identity: 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 Tor. Nothing to install.

What risk level is tor_new_identity? +

tor_new_identity is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit tor_new_identity? +

Yes. Add a rate_limit block to the tor_new_identity 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.

How do I block tor_new_identity completely? +

Set action: deny in the PolicyLayer policy for tor_new_identity. 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.

What MCP server provides tor_new_identity? +

tor_new_identity is provided by the Tor MCP server (rushikeshmore/tor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.