browser_open · Agent Browser MCP Server MCP: Risk & Policy

WHAT IT DOES

What browser_open does on Agent Browser MCP Server

AI agents invoke browser_open to trigger actions in Agent Browser 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 browser_open needs a policy

This tool initiates a browser session by navigating to a URL, which is an external operation that triggers real web interactions. It can access any URL including internal/protected resources, and the session it creates is used for subsequent browser actions (clicks, form fills, etc.), making it an entry point for a chain of potentially high-impact operations.

From the tool's definition URLを開いてブラウザセッションを開始します (Opens a URL and starts a browser session). Supports Basic authentication for protected sites.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_open Rate-limited

browser_open 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_open": {
      "limits": [
        {
          "counter": "browser_open_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 Agent Browser MCP Server, so you can run agents against it safely.

FAQ

Questions about browser_open

What does the browser_open tool do? +

URLを開いてブラウザセッションを開始します。セッションIDが返されるので、以降の操作で使用してください。Basic認証が必要なサイトの場合はbasic_authを指定してください。. It is categorised as a Execute tool in the Agent Browser 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 browser_open? +

Register the Agent Browser MCP Server MCP server in PolicyLayer and add a rule for browser_open: 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 Agent Browser MCP Server. Nothing to install.

What risk level is browser_open? +

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

Can I rate-limit browser_open? +

Yes. Add a rate_limit block to the browser_open 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_open completely? +

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

browser_open is provided by the Agent Browser MCP Server MCP server (nocall-corp/agent-browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.