start_chrome_and_connect

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-and-connect.md

WHAT IT DOES

What start_chrome_and_connect does on Chrome Devtools

AI agents invoke start_chrome_and_connect 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_and_connect is rated High

This tool triggers external operations (Chrome process startup, browser connection, navigation) whose effects depend on the URL argument provided. While it doesn't directly execute code itself, it establishes a debugging connection that enables the broader set of Execute capabilities on this server (execute_javascript, evaluate_in_all_frames).

From the tool's definition Tool description states it "Start Chrome with debugging, connect, and navigate to URL in one step" and "combines browser startup, connection establishment, and navigation into a single operation." The sibling tools include "execute_javascript" and…

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs start_chrome_and_connect 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_and_connect, this is the rule to start with:

start_chrome_and_connect Rate-limited

start_chrome_and_connect 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_and_connect": {
      "limits": [
        {
          "counter": "start_chrome_and_connect_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_and_connect call is checked against it from then on.

FAQ

Questions about start_chrome_and_connect

What does the start_chrome_and_connect tool do? +

Start Chrome with debugging, connect, and navigate to URL in one step. Convenience function that combines browser startup, connection establishment, and navigation into a single operation. Equivalent to calling start_chrome with auto_connect=True and a URL parameter. This function is ideal for quick browser automation tasks where you need to get Chrome running and navigate to a specific page without manual connection management. Args: url: Target URL to navigate to after Chrome startup. Must be a valid URL that Chrome can load. port: TCP port for Chrome remote debugging server (default: 9222). Must be available or already in use by Chrome. headless: Whether to run Chrome in headless mode without GUI. Particularly useful for automated testing scenarios. chrome_path: Custom path to Chrome executable. If not provided, uses automatic platform-specific detection. Returns: Combined status dictionary containing startup, connection, and navigation results. Includes all fields from start_chrome plus navigation status. Note: This is a convenience wrapper around start_chrome with auto_connect=True. For more granular control over the startup process, use start_chrome directly. 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_and_connect? +

Register the Chrome Devtools MCP server in PolicyLayer and add a rule for start_chrome_and_connect: 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_and_connect? +

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

Can I rate-limit start_chrome_and_connect? +

Yes. Add a rate_limit block to the start_chrome_and_connect 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_and_connect completely? +

Set action: deny in the PolicyLayer policy for start_chrome_and_connect. 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_and_connect? +

start_chrome_and_connect 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

generate_and_execute_test on Percepta MCP Server →adb_connect_device on Android Forensics ADB 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 →