navigate · Playwright MCP: Risk & Policy

WHAT IT DOES

What navigate does on Playwright MCP

AI agents invoke navigate 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 navigate needs a policy

Navigation is an executable action that can trigger arbitrary external operations depending on the URL. While not inherently destructive or financial, it can be used to visit malicious sites, trigger unwanted transactions, or cause side effects through JavaScript execution on remote pages.

From the tool's definition Tool performs 'Navigate to a URL' which executes a browser navigation action. This is classified as Execute because it triggers an external operation (browser navigation) whose effects depend on the URL argument provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

navigate Rate-limited

navigate 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": {
    "navigate": {
      "limits": [
        {
          "counter": "navigate_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 navigate

What does the navigate tool do? +

Navigate to a URL. 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 navigate? +

Register the Playwright MCP server in PolicyLayer and add a rule for navigate: 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 navigate? +

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

Can I rate-limit navigate? +

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

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

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