browser_goto · Scrapeless MCP: Risk & Policy

WHAT IT DOES

What browser_goto does on Scrapeless

AI agents invoke browser_goto to trigger actions in Scrapeless. 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_goto needs a policy

This tool drives a real browser to a specified URL, triggering an external browser action whose effects depend on the URL argument. It's not a pure read (it causes navigation side effects in the browser session) and fits Execute as it triggers external operations. Misuse could direct the agent to malicious or unintended sites.

From the tool's definition Navigate browser to a specified URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_goto Rate-limited

browser_goto 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_goto": {
      "limits": [
        {
          "counter": "browser_goto_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 Scrapeless, so you can run agents against it safely.

FAQ

Questions about browser_goto

What does the browser_goto tool do? +

Navigate browser to a specified URL. Restrictions: Only for direct URL navigation, not for searches. Valid: Go to https://google.com. Invalid: Search for. It is categorised as a Execute tool in the Scrapeless 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_goto? +

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

What risk level is browser_goto? +

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

Can I rate-limit browser_goto? +

Yes. Add a rate_limit block to the browser_goto 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_goto completely? +

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

browser_goto is provided by the Scrapeless MCP server (scrapeless-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.