open-browser · TgeBrowser MCP Server MCP: Risk & Policy

WHAT IT DOES

What open-browser does on TgeBrowser MCP Server

AI agents invoke open-browser to trigger actions in TgeBrowser 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 open-browser needs a policy

This tool launches a browser environment/profile and returns a WebSocket URL for automation. It triggers an external operation (spawning a browser process) and enables subsequent automation actions. It is not purely reading data, nor is it destructive or financial — it executes an operation that starts a browser session.

From the tool's definition Open the browser (environment/profile)... After opening, call connect-browser-with-ws with the returned ws URL to enable automation tools (navigate, screenshot, click, etc.)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open-browser Rate-limited

open-browser 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": {
    "open-browser": {
      "limits": [
        {
          "counter": "open-browser_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 TgeBrowser MCP Server, so you can run agents against it safely.

FAQ

Questions about open-browser

What does the open-browser tool do? +

Open the browser (environment/profile). Requires envId OR userIndex. Use get-browser-list first to find envId/userIndex. After opening, call connect-browser-with-ws with the returned ws URL to enable automation tools (navigate, screenshot, click, etc.). It is categorised as a Execute tool in the TgeBrowser 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 open-browser? +

Register the TgeBrowser MCP Server MCP server in PolicyLayer and add a rule for open-browser: 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 TgeBrowser MCP Server. Nothing to install.

What risk level is open-browser? +

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

Can I rate-limit open-browser? +

Yes. Add a rate_limit block to the open-browser 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 open-browser completely? +

Set action: deny in the PolicyLayer policy for open-browser. 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 open-browser? +

open-browser is provided by the TgeBrowser MCP Server MCP server (tuguang2025/tgebrowser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.