start_chrome

SERVERChrome Devtools SOURCEbenjaminr/chrome-devtools-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/benjaminr-chrome-devtools-mcp/start-chrome.md

WHAT IT DOES

What start_chrome does on Chrome Devtools

AI agents invoke start_chrome to trigger actions in Chrome Devtools. 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.

RISK

Why start_chrome is rated High

Starting Chrome with remote debugging enabled and establishing connections to control browser behavior constitutes executing external operations. While not directly destructive or financial, it enables arbitrary browser automation and code execution through the DevTools Protocol, making it an Execute-category tool.

From the tool's definition Tool 'start_chrome' launches Chrome browser with remote debugging enabled and can automatically connect to it.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs start_chrome safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Chrome Devtools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_chrome, this is the rule to start with:

start_chrome Rate-limited

start_chrome 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_chrome": {
      "limits": [
        {
          "counter": "start_chrome_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Chrome Devtools, apply this rule, and every start_chrome call is checked against it from then on.

FAQ

Questions about start_chrome

What does the start_chrome tool do? +

Start Chrome with remote debugging enabled and optionally establish connection. Launches Chrome browser with DevTools Protocol debugging enabled on the specified port. Supports both headless and windowed modes, with automatic executable detection across platforms. Can optionally connect to the started instance and navigate to a specific URL in a single operation. The function handles existing Chrome instances gracefully, detecting if Chrome is already running on the target port and optionally connecting to it rather than attempting to start a new instance. Args: port: TCP port for Chrome remote debugging server (default: 9222). Must be available or already in use by Chrome. url: Initial URL to navigate to after starting Chrome. If provided, Chrome will load this page on startup. headless: Whether to run Chrome in headless mode without GUI. Useful for automated testing and server environments. chrome_path: Custom path to Chrome executable. If not provided, uses automatic detection based on platform. auto_connect: Whether to automatically connect to Chrome and enable debugging domains after startup. Returns: Comprehensive status dictionary containing: - success: Boolean indicating operation success - message: Human-readable status description - data: Detailed information including: - port: Port Chrome is running on - pid: Process ID of Chrome instance (if started) - connected: Whether connection was established - navigated: Whether URL navigation succeeded - alreadyRunning: Whether Chrome was already running Raises: The function handles exceptions internally and returns error responses rather than raising exceptions. Check the 'success' field in the response. Note: Uses a temporary user data directory to avoid conflicts with existing Chrome profiles. The directory location is platform-specific. It is categorised as a Execute tool in the Chrome Devtools 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_chrome? +

Register the Chrome Devtools MCP server in PolicyLayer and add a rule for start_chrome: 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 Chrome Devtools. Nothing to install.

What risk level is start_chrome? +

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

Can I rate-limit start_chrome? +

Yes. Add a rate_limit block to the start_chrome 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_chrome completely? +

Set action: deny in the PolicyLayer policy for start_chrome. 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_chrome? +

start_chrome is provided by the Chrome Devtools MCP server (benjaminr/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Chrome Devtools, and thousands of servers like it.

This server

All 47 Chrome Devtools tools → High-risk tools on this server →

Across the catalogue

start_devtools_monitoring on Percepta MCP Server →team_manager_start_room on Team Manager MCP →start_etw_trace on Procmon → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →