browser_unroute · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_unroute does on Playwright MCP

AI agents invoke browser_unroute to trigger actions in Playwright MCP. 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 browser_unroute needs a policy

In Playwright, 'unroute' removes a previously registered network route/interception handler. This modifies the browser's network interception configuration, which is an execution-level action affecting how requests are processed. With an empty description, confidence is reduced, but based on Playwright API knowledge, this is most likely an Execute-category action that alters browser state.

From the tool's definition Tool name 'browser_unroute' on a Playwright MCP server; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_unroute Rate-limited

browser_unroute 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": {
    "browser_unroute": {
      "limits": [
        {
          "counter": "browser_unroute_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 Playwright MCP, so you can run agents against it safely.

FAQ

Questions about browser_unroute

What does the browser_unroute tool do? +

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

How do I enforce a policy on browser_unroute? +

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

What risk level is browser_unroute? +

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

Can I rate-limit browser_unroute? +

Yes. Add a rate_limit block to the browser_unroute 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 browser_unroute completely? +

Set action: deny in the PolicyLayer policy for browser_unroute. 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 browser_unroute? +

browser_unroute is provided by the Playwright MCP server (naumana3services-maker/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.