browser_start · Selenium MCP: Risk & Policy

WHAT IT DOES

What browser_start does on SeleniumMCP

AI agents invoke browser_start to trigger actions in SeleniumMCP. 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_start needs a policy

While 'browser_start' alone appears passive (merely initializing a session), it is the gateway to Execute-category actions in the Selenium ecosystem. Starting a browser instance enables arbitrary JavaScript execution, user interaction simulation, and external website navigation.

From the tool's definition Tool starts a Selenium browser session, initiating browser automation capabilities. Combined with sibling tools like 'execute_script', 'click', and 'find_element', this enables arbitrary code execution and browser control whose effects depend on subsequent…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_start Rate-limited

browser_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_start": {
      "limits": [
        {
          "counter": "browser_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 SeleniumMCP, so you can run agents against it safely.

FAQ

Questions about browser_start

What does the browser_start tool do? +

Start a Selenium browser session if one is not already running. It is categorised as a Execute tool in the SeleniumMCP 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_start? +

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

What risk level is browser_start? +

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

Can I rate-limit browser_start? +

Yes. Add a rate_limit block to the browser_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_start completely? +

Set action: deny in the PolicyLayer policy for browser_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_start? +

browser_start is provided by the Selenium MCP server (lokii0911/seleniummcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.