chrome-devtools-mcp-parallel

v0.25.3

Published

6 days ago

Chrome DevTools MCP with parallel multi-instance browser support. Drop-in enhancement over chrome-devtools-mcp.

0High
0Medium
0Low

wangkouzhun

chrome devtools mcp parallel multi-instance

Chrome DevTools MCP (Parallel)

Fork of chrome-devtools-mcp that adds parallel multi-instance browser support.

Parallel Mode

Run multiple isolated Chrome instances from a single MCP server process. Each tool call takes an instanceId argument; launch mode (auto-spawn) and CDP mode (reuse a running Chrome via --remote-debugging-port=9222) are both supported.

Drop-in config:

{
  "mcpServers": {
    "chrome-devtools-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "chrome-devtools-mcp-parallel@latest",
        "--headless",
        "--isolated",
        "--max-instances",
        "5"
      ]
    }
  }
}

Binaries shipped:

chrome-devtools-mcp-parallel - parallel multi-instance server (recommended).
chrome-devtools-mcp - upstream single-instance server, unchanged.
chrome-devtools - upstream CLI.

See specs/001-parallel-instances/quickstart.md for the 5-minute tour and PUBLISH.md for release instructions.

Stability Hardening (since v0.25)

The parallel server ships a coordinated stability program: bounded ring buffers for console / network records, on-disk persistence for large artifacts (screenshots, traces, heap snapshots), structured error codes on instance crashes, an automatic 4 GB heap floor, OOM forensic logging, and observability tooling. Defaults are safe out of the box — most users do not need to tune anything. Detailed reference:

📋 Migration guide — every default that changed, every field added, and how to opt back in.
🧱 Data model — runtime entities (Instance state machine, RingBuffer, Artifact, StructuredError, MemorySample, ObservabilitySnapshot, …).
📝 Tool contracts — I/O schemas + error codes for the new management tools (instance_health, instance_recreate, page_artifact_read_summary, system_observe).
📊 Memory & Heap section below for the heap respawn + memory monitor knobs.

Upstream README

The rest of this document is adapted from upstream chrome-devtools-mcp. All package-name references have been rewritten to chrome-devtools-mcp-parallel. Tool reference / CLI options / feature descriptions remain unchanged unless explicitly noted as different for the parallel fork.

Chrome DevTools for Agents (chrome-devtools-mcp) lets your coding agent (such as Gemini, Claude, Cursor or Copilot) control and inspect a live Chrome browser. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of Chrome DevTools for reliable automation, in-depth debugging, and performance analysis. A CLI is also provided for use without MCP.

Tool reference | Changelog | Contributing | Troubleshooting | Design Principles

Key features

Get performance insights: Uses Chrome DevTools to record traces and extract actionable performance insights.
Advanced browser debugging: Analyze network requests, take screenshots and check browser console messages (with source-mapped stack traces).
Reliable automation. Uses puppeteer to automate actions in Chrome and automatically wait for action results.

Disclaimers

chrome-devtools-mcp exposes content of the browser instance to the MCP clients allowing them to inspect, debug, and modify any data in the browser or DevTools. Avoid sharing sensitive or personal information that you don't want to share with MCP clients.

chrome-devtools-mcp officially supports Google Chrome and Chrome for Testing only. Other Chromium-based browsers may work, but this is not guaranteed, and you may encounter unexpected behavior. Use at your own discretion. We are committed to providing fixes and support for the latest version of Extended Stable Chrome.

Performance tools may send trace URLs to the Google CrUX API to fetch real-user experience data. This helps provide a holistic performance picture by presenting field data alongside lab data. This data is collected by the Chrome User Experience Report (CrUX). To disable this, run with the --no-performance-crux flag.

Usage statistics

The parallel server (chrome-devtools-mcp-parallel) does not collect any usage statistics. The --no-usage-statistics flag from the upstream chrome-devtools-mcp bin is still accepted for compatibility but has no effect in parallel mode.

The original chrome-devtools-mcp bin shipped in this package retains its upstream telemetry behaviour; see upstream documentation for details.

Update checks

This fork does not ping the npm registry for update checks. The CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS env variable from upstream is still honoured for compatibility but has no effect in parallel mode.

Requirements

Node.js v20.19 or a newer latest maintenance LTS version.
Chrome current stable version or newer.
npm

Getting started

Add the following config to your MCP client:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp-parallel@latest"]
    }
  }
}

[!NOTE] Using chrome-devtools-mcp-parallel@latest ensures that your MCP client will always use the latest version of the Chrome DevTools MCP server.

If you are interested in doing only basic browser tasks, use the --slim mode:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "chrome-devtools-mcp-parallel@latest",
        "--slim",
        "--headless"
      ]
    }
  }
}

See Slim tool reference.

MCP Client configuration

amp mcp add chrome-devtools -- npx chrome-devtools-mcp-parallel@latest

To use the Chrome DevTools MCP server follow the instructions from Antigravity's docs to install a custom MCP server. Add the following config to the MCP servers config:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "chrome-devtools-mcp-parallel@latest",
        "--browser-url=http://127.0.0.1:9222",
        "-y"
      ]
    }
  }
}

This will make the Chrome DevTools MCP server automatically connect to the browser that Antigravity is using. If you are not using port 9222, make sure to adjust accordingly.

Chrome DevTools MCP will not start the browser instance automatically using this approach because the Chrome DevTools MCP server connects to Antigravity's built-in browser. If the browser is not already running, you have to start it first by clicking the Chrome icon at the top right corner.

Install via CLI (MCP only)

Use the Claude Code CLI to add the Chrome DevTools MCP server (guide):

claude mcp add chrome-devtools --scope user npx chrome-devtools-mcp-parallel@latest

Install as a Plugin (MCP + Skills)

[!NOTE] If you already had Chrome DevTools MCP installed previously for Claude Code, make sure to remove it first from your installation and configuration files.

To install Chrome DevTools MCP with skills, add the marketplace registry in Claude Code:

/plugin marketplace add ChromeDevTools/chrome-devtools-mcp

Then, install the plugin:

/plugin install chrome-devtools-mcp

Restart Claude Code to have the MCP server and skills load (check with /skills).

[!TIP] If the plugin installation fails with a Failed to clone repository error (e.g., HTTPS connectivity issues behind a corporate firewall), see the troubleshooting guide for workarounds, or use the CLI installation method above instead.

codex mcp add chrome-devtools -- npx chrome-devtools-mcp-parallel@latest

On Windows 11

Configure the Chrome install location and increase the startup timeout by updating .codex/config.toml and adding the following env and startup_timeout_ms parameters:

[mcp_servers.chrome-devtools]
command = "cmd"
args = [
    "/c",
    "npx",
    "-y",
    "chrome-devtools-mcp-parallel@latest",
]
env = { SystemRoot="C:\\Windows", PROGRAMFILES="C:\\Program Files" }
startup_timeout_ms = 20_000

Use the Command Code CLI to add the Chrome DevTools MCP server (MCP guide):

cmd mcp add chrome-devtools --scope user npx chrome-devtools-mcp-parallel@latest

Start Copilot CLI:

copilot

Start the dialog to add a new MCP server by running:

/mcp add

Configure the following fields and press CTRL+S to save the configuration:

Server name: chrome-devtools
Server Type: [1] Local
Command: npx -y chrome-devtools-mcp-parallel@latest

Install as a Plugin (Recommended)

The easiest way to get up and running is to install chrome-devtools-mcp as an agent plugin. This bundles the MCP server and all skills together, so your agent gets both the tools and the expert guidance it needs to use them effectively.

Open the Command Palette (Cmd+Shift+P on macOS or Ctrl+Shift+P on Windows/Linux).
Search for and run the Chat: Install Plugin From Source command.
Paste in our repository URL: https://github.com/ChromeDevTools/chrome-devtools-mcp

That's it! Your agent is now supercharged with Chrome DevTools capabilities.

Install as an MCP Server (MCP only)

Click the button to install:

Or install manually:

Follow the VS Code MCP configuration guide using the standard config from above, or use the CLI:

For macOS and Linux:

code --add-mcp '{"name":"io.github.Mokecy/chrome-devtools-mcp-parallel","command":"npx","args":["-y","chrome-devtools-mcp-parallel"],"env":{}}'

For Windows (PowerShell):

code --add-mcp '{"""name""":"""io.github.Mokecy/chrome-devtools-mcp-parallel""","""command""":"""npx""","""args""":["""-y""","""chrome-devtools-mcp-parallel"""]}'

Click the button to install:

Or install manually:

Go to Cursor Settings -> MCP -> New MCP Server. Use the config provided above.

droid mcp add chrome-devtools "npx -y chrome-devtools-mcp-parallel@latest"

Project wide:

# Either MCP only:
gemini mcp add chrome-devtools npx chrome-devtools-mcp-parallel@latest
# Or as a Gemini extension (MCP+Skills):
gemini extensions install --auto-update https://github.com/ChromeDevTools/chrome-devtools-mcp

Globally:

gemini mcp add -s user chrome-devtools npx chrome-devtools-mcp-parallel@latest

Alternatively, follow the MCP guide and use the standard config from above.

In Kiro Settings, go to Configure MCP > Open Workspace or User MCP Config > Use the configuration snippet provided above.

Or, from the IDE Activity Bar > Kiro > MCP Servers > Click Open MCP Config. Use the configuration snippet provided above.

The Chrome DevTools MCP server can be used with Katalon StudioAssist via an MCP proxy.

Step 1: Install the MCP proxy by following the MCP proxy setup guide.

Step 2: Start the Chrome DevTools MCP server with the proxy:

mcp-proxy --transport streamablehttp --port 8080 -- npx -y chrome-devtools-mcp-parallel@latest

Note: You may need to pick another port if 8080 is already in use.

Step 3: In Katalon Studio, add the server to StudioAssist with the following settings:

Connection URL: http://127.0.0.1:8080/mcp
Transport type: HTTP

Once connected, the Chrome DevTools MCP tools will be available in StudioAssist.

Add in ~/.vibe/config.toml:

[[mcp_servers]]
name = "chrome-devtools"
transport = "stdio"
command = "npx"
args = ["chrome-devtools-mcp-parallel@latest"]

Add the following configuration to your opencode.json file. If you don't have one, create it at ~/.config/opencode/opencode.json (guide):

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "chrome-devtools": {
      "type": "local",
      "command": ["npx", "-y", "chrome-devtools-mcp-parallel@latest"]
    }
  }
}

In Qoder Settings, go to MCP Server > + Add > Use the configuration snippet provided above.

Alternatively, follow the MCP guide and use the standard config from above.

Install the Chrome DevTools MCP server using the Qoder CLI (guide):

Project wide:

qodercli mcp add chrome-devtools -- npx chrome-devtools-mcp-parallel@latest

Globally:

qodercli mcp add -s user chrome-devtools -- npx chrome-devtools-mcp-parallel@latest

Click the button to install:

Go to Settings | AI | Manage MCP Servers -> + Add to add an MCP Server. Use the config provided above.

Your first prompt

Enter the following prompt in your MCP Client to check if everything is working:

Check the performance of https://developers.chrome.com

Your MCP client should open the browser and record a performance trace.

[!NOTE] The MCP server will start the browser automatically once the MCP client uses a tool that requires a running browser instance. Connecting to the Chrome DevTools MCP server on its own will not automatically start the browser.

Tools

If you run into any issues, checkout our troubleshooting guide.

Input automation (10 tools)
Navigation automation (6 tools)
Emulation (2 tools)
- emulate
- resize_page
Performance (3 tools)
Network (2 tools)
- get_network_request
- list_network_requests
Debugging (8 tools)
Memory (4 tools)
Extensions (5 tools)
Third-party (2 tools)
- execute_3p_developer_tool
- list_3p_developer_tools
WebMCP (2 tools)
- execute_webmcp_tool
- list_webmcp_tools

Configuration

The Chrome DevTools MCP server supports the following configuration option:

--autoConnect/ --auto-connect If specified, automatically connects to a browser (Chrome 144+) running locally from the user data directory identified by the channel param (default channel is stable). Requires the remote debugging server to be started in the Chrome instance via chrome://inspect/#remote-debugging.
- Type: boolean
- Default: false
--browserUrl/ --browser-url, -u Connect to a running, debuggable Chrome instance (e.g. http://127.0.0.1:9222). For more details see: https://github.com/ChromeDevTools/chrome-devtools-mcp#connecting-to-a-running-chrome-instance.
- Type: string
--wsEndpoint/ --ws-endpoint, -w WebSocket endpoint to connect to a running Chrome instance (e.g., ws://127.0.0.1:9222/devtools/browser/). Alternative to --browserUrl.
- Type: string
--wsHeaders/ --ws-headers Custom headers for WebSocket connection in JSON format (e.g., '{"Authorization":"Bearer token"}'). Only works with --wsEndpoint.
- Type: string
--headless Whether to run in headless (no UI) mode.
- Type: boolean
- Default: false
--executablePath/ --executable-path, -e Path to custom Chrome executable.
- Type: string
--isolated If specified, creates a temporary user-data-dir that is automatically cleaned up after the browser is closed. Defaults to false.
- Type: boolean
--userDataDir/ --user-data-dir Path to the user data directory for Chrome. Default is $HOME/.cache/chrome-devtools-mcp/chrome-profile$CHANNEL_SUFFIX_IF_NON_STABLE
- Type: string
--channel Specify a different Chrome channel that should be used. The default is the stable channel version.
- Type: string
- Choices: canary, dev, beta, stable
--logFile/ --log-file Path to a file to write debug logs to. Set the env variable DEBUG to * to enable verbose logs. Useful for submitting bug reports.
- Type: string
--viewport Initial viewport size for the Chrome instances started by the server. For example, 1280x720. In headless mode, max size is 3840x2160px.
- Type: string
--proxyServer/ --proxy-server Proxy server configuration for Chrome passed as --proxy-server when launching the browser. See https://www.chromium.org/developers/design-documents/network-settings/ for details.
- Type: string
--acceptInsecureCerts/ --accept-insecure-certs If enabled, ignores errors relative to self-signed and expired certificates. Use with caution.
- Type: boolean
--experimentalVision/ --experimental-vision Whether to enable coordinate-based tools such as click_at(x,y). Usually requires a computer-use model able to produce accurate coordinates by looking at screenshots.
- Type: boolean
--experimentalScreencast/ --experimental-screencast Exposes experimental screencast tools (requires ffmpeg). Install ffmpeg https://www.ffmpeg.org/download.html and ensure it is available in the MCP server PATH.
- Type: boolean
--experimentalFfmpegPath/ --experimental-ffmpeg-path Path to ffmpeg executable for screencast recording.
- Type: string
--categoryExperimentalWebmcp/ --category-experimental-webmcp Set to true to enable debugging WebMCP tools. Requires Chrome 149+ with the following flags: --enable-features=WebMCPTesting,DevToolsWebMCPSupport
- Type: boolean
--chromeArg/ --chrome-arg Additional arguments for Chrome. Only applies when Chrome is launched by chrome-devtools-mcp.
- Type: array
--ignoreDefaultChromeArg/ --ignore-default-chrome-arg Explicitly disable default arguments for Chrome. Only applies when Chrome is launched by chrome-devtools-mcp.
- Type: array
--categoryEmulation/ --category-emulation Set to false to exclude tools related to emulation.
- Type: boolean
- Default: true
--categoryPerformance/ --category-performance Set to false to exclude tools related to performance.
- Type: boolean
- Default: true
--categoryNetwork/ --category-network Set to false to exclude tools related to network.
- Type: boolean
- Default: true
--categoryExtensions/ --category-extensions Set to true to include tools related to extensions. Note: This feature is currently only supported with a pipe connection. autoConnect, browserUrl, and wsEndpoint are not supported with this feature until 149 will be released.
- Type: boolean
- Default: false
--categoryExperimentalThirdParty/ --category-experimental-third-party Set to true to enable third-party developer tools exposed by the inspected page itself
- Type: boolean
- Default: false
--performanceCrux/ --performance-crux Set to false to disable sending URLs from performance traces to CrUX API to get field performance data.
- Type: boolean
- Default: true
--usageStatistics/ --usage-statistics Set to false to opt-out of usage statistics collection. Google collects usage data to improve the tool, handled under the Google Privacy Policy (https://policies.google.com/privacy). This is independent from Chrome browser metrics. Disabled if CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS or CI env variables are set.
- Type: boolean
- Default: true
--slim Exposes a "slim" set of 3 tools covering navigation, script execution and screenshots only. Useful for basic browser tasks.
- Type: boolean
--redactNetworkHeaders/ --redact-network-headers If true, redacts some of the network headers considered senstive before returning to the client.
- Type: boolean
- Default: false

Memory & Heap

The parallel server applies a few heap-related defaults so long-running sessions (multi-instance soak tests, big DOM snapshots, hour-long traces) don't trip V8's stock ~1.5 GB heap cap. You almost never need to change these — they're documented mostly for operators investigating crash logs.

Defaults

| Setting | Default | Override | | --------------------------- | ------------------------- | --------------------------------------------------- | | Node --max-old-space-size | 4096 MB | --heap-size <MB> (CLI) > CDM_HEAP_SIZE_MB (env) | | Memory sampling interval | 60 s | --mem-sample-interval-sec <N> | | Warn threshold | 80 % of heap_size_limit | --mem-warn-pct <N> | | Danger threshold | 95 % of heap_size_limit | --mem-danger-pct <N> |

Heap self-respawn (FR-019)

On boot the server inspects v8.getHeapStatistics().heap_size_limit. If it sits below the resolved heap target, the entry script re-execs itself as a child process with NODE_OPTIONS="--max-old-space-size=<resolvedMB>" and exits with the child's status code. A CDM_HEAP_RESPAWNED=1 env var marks the child so we never recurse. To opt out, pass an explicit --heap-size matching what your launcher already configures.

Memory monitor (FR-022)

Once a minute (configurable) the server samples process.memoryUsage() + v8.getHeapStatistics():

Warn band (≥ warnPct): one stderr line per rising edge: [MemoryMonitor][WARN] heap 82.4% (used=3.4GB / limit=4.0GB, rss=4.1GB). A best-effort global.gc?.() runs if Node was launched with --expose-gc.
Danger band (≥ dangerPct): every tick prints [MemoryMonitor][DANGER] heap 96.1% — closing idle resources and the server proactively closes one idle (state=ready, no in-flight tool call) instance to reclaim heap.

The last 60 samples are kept in a ring buffer; the crash logger snapshots them on its way out (see below).

Physical-memory clamp (FR-021)

If the resolved heap exceeds 75 % of total system memory the server clamps it to that ceiling and prints a single warning to stderr:

[HeapSelfRespawn] requested heap 8192MB exceeds physical-memory safety ratio;
                  clamping to 6144MB (total=8192MB)

Crash log (FR-023 / SC-008)

A process-level handler installed at boot writes a structured JSON record to <artifactDir>/crashes/<ISO>.log for every uncaughtException / unhandledRejection, then the runtime exits with code 1. Each record contains:

{
  "ts": "2026-...",
  "kind": "uncaughtException",
  "error": { "message": "...", "stack": "...", "name": "RangeError" },
  "activeInstances": [ ...InstanceHealthSnapshot ],
  "memorySamples":   [ ...MemorySample (last 60) ],
  "recentToolCalls": [ ...ToolCallRecord (last 20) ]
}

<artifactDir> is --artifact-dir when set, otherwise the per-pid ephemeral slot under the OS tmpdir. Forensics tip: open the file, grep heapPct to see the trajectory leading to the crash, and recentToolCalls for the last operations the server was working on.

Pass them via the args property in the JSON configuration. For example:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "chrome-devtools-mcp-parallel@latest",
        "--channel=canary",
        "--headless=true",
        "--isolated=true"
      ]
    }
  }
}

Connecting via WebSocket with custom headers

You can connect directly to a Chrome WebSocket endpoint and include custom headers (e.g., for authentication):

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "chrome-devtools-mcp-parallel@latest",
        "--wsEndpoint=ws://127.0.0.1:9222/devtools/browser/<id>",
        "--wsHeaders={\"Authorization\":\"Bearer YOUR_TOKEN\"}"
      ]
    }
  }
}

To get the WebSocket endpoint from a running Chrome instance, visit http://127.0.0.1:9222/json/version and look for the webSocketDebuggerUrl field.

You can also run npx chrome-devtools-mcp-parallel@latest --help to see all available configuration options.

Concepts

User data directory

chrome-devtools-mcp starts a Chrome's stable channel instance using the following user data directory:

Linux / macOS: $HOME/.cache/chrome-devtools-mcp/chrome-profile-$CHANNEL
Windows: %HOMEPATH%/.cache/chrome-devtools-mcp/chrome-profile-$CHANNEL

The user data directory is not cleared between runs and shared across all instances of chrome-devtools-mcp. Set the isolated option to true to use a temporary user data dir instead which will be cleared automatically after the browser is closed.

Connecting to a running Chrome instance

By default, the Chrome DevTools MCP server will start a new Chrome instance with a dedicated profile. This might not be ideal in all situations:

If you would like to maintain the same application state when alternating between manual site testing and agent-driven testing.
When the MCP needs to sign into a website. Some accounts may prevent sign-in when the browser is controlled via WebDriver (the default launch mechanism for the Chrome DevTools MCP server).
If you're running your LLM inside a sandboxed environment, but you would like to connect to a Chrome instance that runs outside the sandbox.

In these cases, start Chrome first and let the Chrome DevTools MCP server connect to it. There are two ways to do so:

Automatic connection (available in Chrome 144): best for sharing state between manual and agent-driven testing.
Manual connection via remote debugging port: best when running inside a sandboxed environment.

Automatically connecting to a running Chrome instance

Step 1: Set up remote debugging in Chrome

In Chrome (>= M144), do the following to set up remote debugging:

Navigate to chrome://inspect/#remote-debugging to enable remote debugging.
Follow the dialog UI to allow or disallow incoming debugging connections.

Step 2: Configure Chrome DevTools MCP server to automatically connect to a running Chrome Instance

To connect the chrome-devtools-mcp server to the running Chrome instance, use --autoConnect command line argument for the MCP server.

The following code snippet is an example configuration for gemini-cli:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["chrome-devtools-mcp-parallel@latest", "--autoConnect"]
    }
  }
}

Step 3: Test your setup

Make sure your browser is running. Open gemini-cli and run the following prompt:

Check the performance of https://developers.chrome.com

[!NOTE] The autoConnect option requires the user to start Chrome. If the user has multiple active profiles, the MCP server will connect to the default profile (as determined by Chrome). The MCP server has access to all open windows for the selected profile.

The Chrome DevTools MCP server will try to connect to your running Chrome instance. It shows a dialog asking for user permission.

Clicking Allow results in the Chrome DevTools MCP server opening developers.chrome.com and taking a performance trace.

Manual connection using port forwarding

You can connect to a running Chrome instance by using the --browser-url option. This is useful if you are running the MCP server in a sandboxed environment that does not allow starting a new Chrome instance.

Here is a step-by-step guide on how to connect to a running Chrome instance:

Step 1: Configure the MCP client

Add the --browser-url option to your MCP client configuration. The value of this option should be the URL of the running Chrome instance. http://127.0.0.1:9222 is a common default.

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": [
        "chrome-devtools-mcp-parallel@latest",
        "--browser-url=http://127.0.0.1:9222"
      ]
    }
  }
}

Step 2: Start the Chrome browser

[!WARNING] Enabling the remote debugging port opens up a debugging port on the running browser instance. Any application on your machine can connect to this port and control the browser. Make sure that you are not browsing any sensitive websites while the debugging port is open.

Start the Chrome browser with the remote debugging port enabled. Make sure to close any running Chrome instances before starting a new one with the debugging port enabled. The port number you choose must be the same as the one you specified in the --browser-url option in your MCP client configuration.

For security reasons, Chrome requires you to use a non-default user data directory when enabling the remote debugging port. You can specify a custom directory using the --user-data-dir flag. This ensures that your regular browsing profile and data are not exposed to the debugging session.

macOS

/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-profile-stable

Linux

/usr/bin/google-chrome --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-profile-stable

Windows

"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222 --user-data-dir="%TEMP%\chrome-profile-stable"

Step 3: Test your setup

After configuring the MCP client and starting the Chrome browser, you can test your setup by running a simple prompt in your MCP client:

Check the performance of https://developers.chrome.com

Your MCP client should connect to the running Chrome instance and receive a performance report.

If you hit VM-to-host port forwarding issues, see the "Remote debugging between virtual machine (VM) and host fails"section in docs/troubleshooting.md.

For more details on remote debugging, see the Chrome DevTools documentation.

Debugging Chrome on Android

Please consult these instructions.

Known limitations

See Troubleshooting.

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

Chrome DevTools MCP (Parallel)

Parallel Mode

Stability Hardening (since v0.25)

Upstream README

Tool reference | Changelog | Contributing | Troubleshooting | Design Principles

Key features

Disclaimers

Usage statistics

Update checks

Requirements

Getting started

MCP Client configuration

Your first prompt

Tools

Configuration

Memory & Heap

Defaults

Heap self-respawn (FR-019)

Memory monitor (FR-022)

Physical-memory clamp (FR-021)

Crash log (FR-023 / SC-008)

Connecting via WebSocket with custom headers

Concepts

User data directory

Connecting to a running Chrome instance

Automatically connecting to a running Chrome instance

Manual connection using port forwarding

Debugging Chrome on Android

Known limitations