browser_forward · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What browser_forward does on Claude Flow

AI agents invoke browser_forward to trigger actions in Claude Flow. 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_forward needs a policy

This tool controls a real browser instance, executing navigation actions that trigger JavaScript, maintain session state (cookies), and interact with live web applications. Browser automation can cause side effects depending on the pages visited (form submissions, authenticated actions, etc.), placing it firmly in Execute.

From the tool's definition Navigate forward in browser history ... you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_forward Rate-limited

browser_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_forward": {
      "limits": [
        {
          "counter": "browser_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 Claude Flow, so you can run agents against it safely.

FAQ

Questions about browser_forward

What does the browser_forward tool do? +

Navigate forward in browser history Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. For static HTML pages, native WebFetch is faster and free. It is categorised as a Execute tool in the Claude Flow 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_forward? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for browser_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 Claude Flow. Nothing to install.

What risk level is browser_forward? +

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

Can I rate-limit browser_forward? +

Yes. Add a rate_limit block to the browser_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_forward completely? +

Set action: deny in the PolicyLayer policy for browser_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_forward? +

browser_forward is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.