start_browser · MCP Selenium Server MCP: Risk & Policy

WHAT IT DOES

What start_browser does on MCP Selenium Server

AI agents invoke start_browser to trigger actions in MCP Selenium 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 start_browser needs a policy

Starting a browser is an Execute action because it launches an external process whose effects (resource consumption, network access, potential side effects from auto-loaded pages) depend on runtime configuration and the browser's initial state. While not inherently destructive, it triggers external system operations and cannot be safely assumed to be read-only.

From the tool's definition Tool name 'start_browser' and description 'launches browser' indicate initiation of an external browser process, which is an executable operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_browser Rate-limited

start_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": {
    "start_browser": {
      "limits": [
        {
          "counter": "start_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 MCP Selenium Server, so you can run agents against it safely.

FAQ

Questions about start_browser

What does the start_browser tool do? +

launches browser. It is categorised as a Execute tool in the MCP Selenium 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 start_browser? +

Register the MCP Selenium Server MCP server in PolicyLayer and add a rule for start_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 MCP Selenium Server. Nothing to install.

What risk level is start_browser? +

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

Can I rate-limit start_browser? +

Yes. Add a rate_limit block to the start_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 start_browser completely? +

Set action: deny in the PolicyLayer policy for start_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 start_browser? +

start_browser is provided by the MCP Selenium Server MCP server (sapangupta63/mcp-selenium-extended). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.