open_login_window · Social MCP: Risk & Policy

WHAT IT DOES

What open_login_window does on Social

AI agents invoke open_login_window to trigger actions in Social. 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_login_window needs a policy

This tool launches an external browser process (Chromium), which is an Execute-category action — it triggers an external application. While the immediate purpose is to allow manual login, the act of spawning a browser process with potential session access to Facebook constitutes a meaningful external operation.

From the tool's definition Launch visible Chromium browser so you can manually log in to Facebook.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open_login_window Rate-limited

open_login_window 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_login_window": {
      "limits": [
        {
          "counter": "open_login_window_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 Social, so you can run agents against it safely.

FAQ

Questions about open_login_window

What does the open_login_window tool do? +

Launch visible Chromium browser so you can manually log in to Facebook. It is categorised as a Execute tool in the Social 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_login_window? +

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

What risk level is open_login_window? +

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

Can I rate-limit open_login_window? +

Yes. Add a rate_limit block to the open_login_window 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_login_window completely? +

Set action: deny in the PolicyLayer policy for open_login_window. 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_login_window? +

open_login_window is provided by the Social MCP server (whypuss/ai-cdp-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.