browser_navigate_forward · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_navigate_forward does on Playwright MCP

AI agents invoke browser_navigate_forward 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_navigate_forward needs a policy

Navigation actions qualify as Execute rather than Write because they trigger code execution in external contexts (web pages, third-party servers) and their side effects depend on the target page's behavior. An AI agent misusing this could navigate to malicious sites, trigger unintended transactions, or expose sensitive information.

From the tool's definition Tool performs 'Go forward to the next page' — a browser navigation action that executes a state-changing operation (modifies browser history position and loads external content).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_navigate_forward Rate-limited

browser_navigate_forward 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_navigate_forward": {
      "limits": [
        {
          "counter": "browser_navigate_forward_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_navigate_forward

What does the browser_navigate_forward tool do? +

Go forward to the next page. 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_navigate_forward? +

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

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

Can I rate-limit browser_navigate_forward? +

Yes. Add a rate_limit block to the browser_navigate_forward 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_navigate_forward completely? +

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

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