puppeteer_navigate · Puppeteer MCP Server MCP: Risk & Policy

WHAT IT DOES

What puppeteer_navigate does on Puppeteer MCP Server

AI agents invoke puppeteer_navigate to trigger actions in Puppeteer MCP Server. 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 puppeteer_navigate needs a policy

While navigation might seem like a benign Read operation, it is classified as Execute because: (1) navigating to a URL can trigger arbitrary server-side code, JavaScript execution, and third-party service calls; (2) the Puppeteer context includes 'executing JavaScript in the browser,' indicating the tool is part of a code-execution platform; (3) the blast radius is high—a malicious URL could compromise credentials,…

From the tool's definition The tool performs browser navigation to arbitrary URLs via Puppeteer, which can trigger code execution, API calls, side effects, and data fetches depending on the target URL.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

puppeteer_navigate Rate-limited

puppeteer_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": {
    "puppeteer_navigate": {
      "limits": [
        {
          "counter": "puppeteer_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 Puppeteer MCP Server, so you can run agents against it safely.

FAQ

Questions about puppeteer_navigate

What does the puppeteer_navigate tool do? +

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

How do I enforce a policy on puppeteer_navigate? +

Register the Puppeteer MCP Server MCP server in PolicyLayer and add a rule for puppeteer_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 Puppeteer MCP Server. Nothing to install.

What risk level is puppeteer_navigate? +

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

Can I rate-limit puppeteer_navigate? +

Yes. Add a rate_limit block to the puppeteer_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 puppeteer_navigate completely? +

Set action: deny in the PolicyLayer policy for puppeteer_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 puppeteer_navigate? +

puppeteer_navigate is provided by the Puppeteer MCP Server MCP server (lijingle1/puppeteer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.