browser_console_start · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_console_start does on Browser

AI agents invoke browser_console_start 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_console_start needs a policy

Starting console log capture is not a passive read; it triggers an ongoing process within the browser that intercepts and records console output. This is an Execute action as it initiates a side-effectful browser operation. Severity is medium because misuse could expose sensitive information logged to the console, but it does not directly modify or destroy data.

From the tool's definition 'Start capturing browser console logs' — initiates an active monitoring/capture process in the browser

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_console_start Rate-limited

browser_console_start 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_console_start": {
      "limits": [
        {
          "counter": "browser_console_start_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_console_start

What does the browser_console_start tool do? +

Start capturing browser console logs (console.log, console.error, console.warn, etc.) (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_console_start? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_console_start: 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_console_start? +

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

Can I rate-limit browser_console_start? +

Yes. Add a rate_limit block to the browser_console_start 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_console_start completely? +

Set action: deny in the PolicyLayer policy for browser_console_start. 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_console_start? +

browser_console_start 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.