browser_tabs · Browser Pool MCP: Risk & Policy

WHAT IT DOES

What browser_tabs does on Browser Pool

AI agents invoke browser_tabs to trigger actions in Browser Pool. 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_tabs needs a policy

Tab management in a browser context involves executing browser actions (opening, closing, or switching tabs). This falls under Execute as it triggers external operations in the browser session. The description is minimal, lowering confidence. Severity is medium since misuse could affect active browser sessions but has limited blast radius compared to full code execution or destructive operations.

From the tool's definition Tool name 'browser_tabs' with description 'Manage tabs' — managing browser tabs implies creating, switching, or closing tabs within a Playwright browser session, which triggers external browser operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_tabs Rate-limited

browser_tabs 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_tabs": {
      "limits": [
        {
          "counter": "browser_tabs_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 Browser Pool, so you can run agents against it safely.

FAQ

Questions about browser_tabs

What does the browser_tabs tool do? +

Manage tabs. It is categorised as a Execute tool in the Browser Pool 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_tabs? +

Register the Browser Pool MCP server in PolicyLayer and add a rule for browser_tabs: 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 Browser Pool. Nothing to install.

What risk level is browser_tabs? +

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

Can I rate-limit browser_tabs? +

Yes. Add a rate_limit block to the browser_tabs 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_tabs completely? +

Set action: deny in the PolicyLayer policy for browser_tabs. 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_tabs? +

browser_tabs is provided by the Browser Pool MCP server (omgeverdo/browser-pool-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.