browser_net_start_monitoring · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_net_start_monitoring does on Browser

AI agents invoke browser_net_start_monitoring to trigger actions in Browser. 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_net_start_monitoring needs a policy

While network monitoring itself is primarily observational (Read-like), in the context of a browser automation tool with Playwright/CDP capabilities, network monitoring is typically paired with the ability to intercept, block, or modify requests. The tool enables active control of browser operations and network flows, making it Execute rather than pure Read.

From the tool's definition Tool name includes 'start_monitoring' and description states it monitors 'network requests with detailed timing'. This is part of a browser automation system using Playwright that enables 'programmatic control of Chrome' with CDP-based diagnostics.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_net_start_monitoring Rate-limited

browser_net_start_monitoring 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_net_start_monitoring": {
      "limits": [
        {
          "counter": "browser_net_start_monitoring_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, so you can run agents against it safely.

FAQ

Questions about browser_net_start_monitoring

What does the browser_net_start_monitoring tool do? +

Start monitoring network requests with detailed timing (see browser_docs). It is categorised as a Execute tool in the Browser 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_net_start_monitoring? +

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

What risk level is browser_net_start_monitoring? +

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

Can I rate-limit browser_net_start_monitoring? +

Yes. Add a rate_limit block to the browser_net_start_monitoring 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_net_start_monitoring completely? +

Set action: deny in the PolicyLayer policy for browser_net_start_monitoring. 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_net_start_monitoring? +

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