1Browser MCP

Fork of ChromeDevTools/chrome-devtools-mcp prepared for 1Browser.

npm: @the1browser/onebrowser-mcp · repo: the1browser/1browser-devtools-mcp

onebrowser-mcp lets your coding agent (such as Antigravity, Claude, Cursor or Copilot) control and inspect a live 1Browser session. It acts as a Model-Context-Protocol (MCP) server, giving your AI coding assistant access to the full power of DevTools for reliable automation, in-depth debugging, and performance analysis. A CLI is also provided for use without MCP.

• 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 1Browser and automatically wait for action results.

1Browser adds experimental DevTools Protocol methods in the Browser domain for local automation of persistent profiles, fingerprint masking, proxy settings, and account auth state. The MCP tools in docs/tool-reference-one-browser.md are thin wrappers over these CDP methods, and the TypeScript augmentation shipped in src/types/browser-profiles.d.ts adds them to devtools-protocol command typings.

Available Browser.* methods:

Browser.login opens the 1Browser web login page and returns the opened target. Use Browser.signin for the email/password backend auth flow. Auth responses do not expose access or refresh tokens to the CDP client.

onebrowser-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.

onebrowser-mcp is prepared for 1Browser 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.

Google collects usage statistics (such as tool invocation success rates, latency, and environment information) to improve the reliability and performance of 1Browser MCP.

Data collection is enabled by default. You can opt-out by passing the --no-usage-statistics flag when starting the server:

"args": ["-y", "@the1browser/onebrowser-mcp@latest", "--no-usage-statistics"]

Google handles this data in accordance with the Google Privacy Policy.

Google's collection of usage statistics for 1Browser MCP is independent from the Chrome browser's usage statistics. Opting out of Chrome metrics does not automatically opt you out of this tool, and vice-versa.

Collection is disabled if CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS or CI env variables are set.

By default, the server periodically checks the npm registry for updates and logs a notification when a newer version is available. You can disable these update checks by setting the CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS environment variable.

• Node.js LTS version.
• 1browser current stable version or newer.
• npm

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": ["-y", "@the1browser/onebrowser-mcp@latest"]
    }
  }
}

Add this to your MCP client config and you're done. Works with Claude Code (~/.mcp.json), Cursor (Settings → MCP), VS Code Copilot, and any other MCP client.

git clone https://github.com/the1browser/1browser-devtools-mcp.git
cd 1browser-devtools-mcp
npm install
npm run build

Run npm run build again after git pull when you update the repo.

Then point your MCP config at the built CLI with an absolute path:

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "node",
      "args": [
        "/absolute/path/to/1browser-devtools-mcp/build/src/bin/chrome-devtools-mcp.js"
      ]
    }
  }
}

This works with Claude Code (~/.mcp.json), Cursor (Settings → MCP → New MCP Server, or mcp.json), VS Code Copilot, and any other MCP client.

If 1Browser is not detected automatically, set ONEBROWSER_PATH or pass --executablePath:

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "node",
      "args": [
        "/absolute/path/to/1browser-devtools-mcp/build/src/bin/chrome-devtools-mcp.js",
        "--executablePath",
        "/Applications/1Browser.app/Contents/MacOS/1Browser"
      ]
    }
  }
}

The server has two modes: launch a new instance (default) or attach to your existing 1Browser window.

With the basic config above, the server spawns a dedicated 1Browser instance with its own profile. Your existing 1Browser windows are untouched. This is the simplest mode - no extra setup needed.

If you want the MCP server to control the 1Browser window you already have open (same tabs, cookies, logins), you need to start 1Browser with remote debugging enabled.

Step 1: Quit 1Browser completely, then relaunch with the debugging flag:

# macOS
open -a "1Browser" --args --remote-debugging-port=9222

# Linux
1browser --remote-debugging-port=9222

# Windows
"C:\Program Files\1Browser\1Browser\Application\1browser.exe" --remote-debugging-port=9222

Tip: To always start 1Browser with remote debugging, add --remote-debugging-port=9222 to 1Browser's launch shortcut or shell alias so you never have to think about it again.

Step 2: Add --browserUrl to your MCP config:

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "@the1browser/onebrowser-mcp@latest",
        "--browserUrl",
        "http://localhost:9222"
      ]
    }
  }
}

Or if running from source:

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "node",
      "args": [
        "/absolute/path/to/1browser-devtools-mcp/build/src/bin/chrome-devtools-mcp.js",
        "--browserUrl",
        "http://localhost:9222"
      ]
    }
  }
}

Without --browserUrl, the server will always launch a new instance. With it, the server attaches to your running 1Browser instead.

Warning: The remote debugging port lets any application on your machine control the browser. Be mindful of sensitive websites while it's open.

Run --help to see every flag:

node /absolute/path/to/1browser-devtools-mcp/build/src/bin/chrome-devtools-mcp.js --help

An integration test suite exercises all MCP tools against a running 1Browser instance:

# Launch 1Browser with remote debugging
open -a "1Browser" --args --remote-debugging-port=9222

# Run the test suite
npm run test

Tests cover navigation, snapshots, screenshots, script execution, input automation (click/fill/drag/upload), dialogs, console, network, emulation, performance tracing, memory snapshots, and Lighthouse audits.

Add the following config to your MCP client:

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": ["-y", "@the1browser/onebrowser-mcp@latest"]
    }
  }
}

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

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "@the1browser/onebrowser-mcp@latest",
        "--slim",
        "--headless"
      ]
    }
  }
}

See Slim tool reference.

amp mcp add onebrowser-devtools -- npx @the1browser/onebrowser-mcp@latest

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "@the1browser/onebrowser-mcp@latest",
        "--browser-url=http://127.0.0.1:9222"
      ]
    }
  }
}

claude mcp add onebrowser-devtools --scope user npx @the1browser/onebrowser-mcp@latest

/plugin marketplace add the1browser/1browser-devtools-mcp

/plugin install onebrowser-mcp@onebrowser-mcp-plugins

codex mcp add onebrowser-devtools -- npx @the1browser/onebrowser-mcp@latest

[mcp_servers.onebrowser-devtools]
command = "cmd"
args = [
    "/c",
    "npx",
    "-y",
    "@the1browser/onebrowser-mcp@latest",
]
env = { SystemRoot="C:\\Windows", PROGRAMFILES="C:\\Program Files" }
startup_timeout_ms = 20_000

cmd mcp add onebrowser-devtools --scope user npx @the1browser/onebrowser-mcp@latest

copilot

/mcp add

code --add-mcp '{"name":"io.github.the1browser/onebrowser-mcp","command":"npx","args":["-y","@the1browser/onebrowser-mcp@latest"],"env":{}}'

code --add-mcp '{"""name""":"""io.github.the1browser/onebrowser-mcp""","""command""":"""npx""","""args""":["""-y""","""@the1browser/onebrowser-mcp@latest"""]}'

droid mcp add onebrowser-devtools "npx -y @the1browser/onebrowser-mcp@latest"

# Either MCP only:
gemini mcp add onebrowser-devtools npx @the1browser/onebrowser-mcp@latest
# Or as a Gemini extension (MCP+Skills):
gemini extensions install --auto-update https://github.com/the1browser/1browser-devtools-mcp

gemini mcp add -s user onebrowser-devtools npx @the1browser/onebrowser-mcp@latest

grok mcp add onebrowser-devtools npx @the1browser/onebrowser-mcp@latest

mcp-proxy --transport streamablehttp --port 8080 -- npx -y @the1browser/onebrowser-mcp@latest

[[mcp_servers]]
name = "onebrowser-devtools"
transport = "stdio"
command = "npx"
args = ["@the1browser/onebrowser-mcp@latest"]

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "onebrowser-devtools": {
      "type": "local",
      "command": ["npx", "-y", "@the1browser/onebrowser-mcp@latest"]
    }
  }
}

qodercli mcp add onebrowser-devtools -- npx @the1browser/onebrowser-mcp@latest

qodercli mcp add -s user onebrowser-devtools -- npx @the1browser/onebrowser-mcp@latest

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.

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

For a first-time 1Browser session, call the login tool first. It launches the browser login page so the user can authorize 1Browser and then use the full browser feature set.

• Input automation (10 tools)
  • click
  • drag
  • fill
  • fill_form
  • handle_dialog
  • hover
  • press_key
  • type_text
  • upload_file
  • click_at
• Navigation automation (6 tools)
  • close_page
  • list_pages
  • navigate_page
  • new_page
  • select_page
  • wait_for
• Emulation (2 tools)
  • emulate
  • resize_page
• Performance (3 tools)
  • performance_analyze_insight
  • performance_start_trace
  • performance_stop_trace
• Network (2 tools)
  • get_network_request
  • list_network_requests
• Debugging (28 tools)
  • check_proxy_connection
  • create_profile
  • create_window_for_profile
  • delete_profile
  • evaluate_script
  • generate_fingerprint
  • get_auth_state
  • get_available_profile_creation_count
  • get_console_message
  • get_fingerprint_setting
  • get_fingerprint_settings
  • get_profiles
  • get_proxy_settings
  • lighthouse_audit
  • list_console_messages
  • login
  • logout
  • request_new_proxy
  • set_fingerprint_setting
  • set_proxy_settings
  • set_proxy_type
  • signin
  • signup
  • take_screenshot
  • take_snapshot
  • verify
  • screencast_start
  • screencast_stop
• Memory (11 tools)
  • take_heapsnapshot
  • close_heapsnapshot
  • compare_heapsnapshots
  • get_heapsnapshot_class_nodes
  • get_heapsnapshot_details
  • get_heapsnapshot_dominators
  • get_heapsnapshot_duplicate_strings
  • get_heapsnapshot_edges
  • get_heapsnapshot_retainers
  • get_heapsnapshot_retaining_paths
  • get_heapsnapshot_summary
• Extensions (5 tools)
  • install_extension
  • list_extensions
  • reload_extension
  • trigger_extension_action
  • uninstall_extension
• Third-party (2 tools)
  • execute_3p_developer_tool
  • list_3p_developer_tools
• WebMCP (2 tools)
  • execute_webmcp_tool
  • list_webmcp_tools

The 1Browser MCP server supports the following configuration option:

• --autoConnect/ --auto-connect If specified, automatically connects to a running local 1Browser instance using its default user data directory. Requires the remote debugging server to be started 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/the1browser/1browser-devtools-mcp#connecting-to-a-running-chrome-instance.

  • Type: string
  • Default: false

• --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
  • Default: false

• --wsHeaders/ --ws-headers Custom headers for WebSocket connection in JSON format (e.g., '{"Authorization":"Bearer token"}'). Only works with --wsEndpoint.

  • Type: string
  • Default: false

• --headless Whether to run in headless (no UI) mode.

  • Type: boolean
  • Default: false

• --executablePath/ --executable-path, -e Path to a custom 1Browser executable. Can also be set via ONEBROWSER_PATH.

  • Type: string
  • Default: false

• --isolated If specified, creates a temporary user-data-dir that is automatically cleaned up after the browser is closed. Defaults to false.

  • Type: boolean
  • Default: false

• --userDataDir/ --user-data-dir Path to the user data directory. With --auto-connect, the default is the platform-specific 1Browser user data directory.

  • Type: string
  • Default: false

• --channel Specify a different Chrome channel that should be used. The default is the stable channel version.

  • Type: string
  • Choices: canary, dev, beta, stable
  • Default: false

• --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
  • Default: false

• --viewport Initial viewport size for the Chrome instances started by the server. For example, 1280x720. In headless mode, max size is 3840x2160px.

  • Type: string
  • Default: false

• --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
  • Default: false

• --acceptInsecureCerts/ --accept-insecure-certs If enabled, ignores errors relative to self-signed and expired certificates. Use with caution.

  • Type: boolean
  • Default: false

• --experimentalPageIdRouting/ --experimental-page-id-routing Whether to expose pageId on page-scoped tools and route requests by page ID (useful for concurrent agent sessions).

  • Type: boolean
  • Default: false

• --experimentalDevtools/ --experimental-devtools Whether to enable automation over DevTools targets

  • Type: boolean
  • Default: false

• --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
  • Default: false

• --memoryDebugging/ --memory-debugging, -experimentalMemory Whether to enable memory debugging tools.

  • Type: boolean
  • Default: false

• --experimentalStructuredContent/ --experimental-structured-content Whether to output structured formatted content.

  • Type: boolean
  • Default: false

• --experimentalIncludeAllPages/ --experimental-include-all-pages Whether to include all kinds of pages such as webviews or background pages as pages.

  • Type: boolean
  • Default: false

• --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
  • Default: false

• --experimentalFfmpegPath/ --experimental-ffmpeg-path Path to ffmpeg executable for screencast recording.

  • Type: string
  • Default: false

• --categoryExperimentalWebmcp/ --category-experimental-webmcp Set to true to enable debugging WebMCP tools. Requires Chrome 149+ with the following flags: --enable-features=WebMCP,DevToolsWebMCPSupport

  • Type: boolean
  • Default: false

• --chromeArg/ --chrome-arg Additional arguments for Chrome. Only applies when Chrome is launched by chrome-devtools-mcp.

  • Type: array
  • Default: false

• --blockedUrlPattern/ --blocked-url-pattern Restricts browser's network access by blocking specified URL patterns (uses https://urlpattern.spec.whatwg.org/). Silently detaches from targets with blocked URLs upon connection, and blocks runtime requests (including navigations and subresources). Accepts an array of patterns.

  • Type: array
  • Default: false

• --allowedUrlPattern/ --allowed-url-pattern Restricts browser's network access by allowing only specified URL patterns (uses https://urlpattern.spec.whatwg.org/). Requires Chrome 149+. Silently detaches from targets with unallowed URLs upon connection, and blocks runtime requests (including navigations and subresources). Accepts an array of patterns.

  • Type: array
  • Default: false

• --ignoreDefaultChromeArg/ --ignore-default-chrome-arg Explicitly disable default arguments for Chrome. Only applies when Chrome is launched by chrome-devtools-mcp.

  • Type: array
  • Default: false

• --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

• --screenshotFormat/ --screenshot-format Override the default output format used by take_screenshot when the caller does not specify one. JPEG and WebP are ~3-5x smaller than PNG, which helps reduce context size in AI conversations. Unset preserves the existing default ("png").

  • Type: string
  • Choices: jpeg, png, webp
  • Default: false

• --screenshotQuality/ --screenshot-quality Override the default compression quality (0-100) used by take_screenshot for JPEG and WebP when the caller does not specify one. Lower values mean smaller files. Ignored for PNG. Unset preserves the Puppeteer default.

  • Type: number
  • Default: false

• --screenshotMaxWidth/ --screenshot-max-width Maximum width in pixels for screenshots. If the captured image is wider, it is downscaled (preserving aspect ratio) before being returned. Reduces context size in AI conversations. Unset means no resize.

  • Type: number
  • Default: false

• --screenshotMaxHeight/ --screenshot-max-height Maximum height in pixels for screenshots. If the captured image is taller, it is downscaled (preserving aspect ratio) before being returned. Can be combined with --screenshot-max-width; the smaller scale factor wins. Unset means no resize.

  • Type: number
  • Default: false

• --slim Exposes a "slim" set of 3 tools covering navigation, script execution and screenshots only. Useful for basic browser tasks.

  • Type: boolean
  • Default: false

• --redactNetworkHeaders/ --redact-network-headers If true, redacts some of the network headers considered sensitive before returning to the client.

  • Type: boolean
  • Default: false

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

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "@the1browser/onebrowser-mcp@latest",
        "--channel=canary",
        "--headless=true",
        "--isolated=true"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "@the1browser/onebrowser-mcp@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 @the1browser/onebrowser-mcp@latest --help to see all available configuration options.

Most MCP clients start one 1Browser MCP server per conversation. If your client shares a single server instance across concurrent agents or subagents, start the server with --experimentalPageIdRouting. This exposes pageId on page-scoped tools so each agent can route tool calls to the tab it is working with.

{
  "mcpServers": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "@the1browser/onebrowser-mcp@latest",
        "--experimentalPageIdRouting"
      ]
    }
  }
}

If you run multiple independent MCP client sessions and want each session to launch its own temporary Chrome profile, also pass --isolated. This avoids sharing the default 1Browser MCP user data directory between those server instances.

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.

By default, the 1Browser 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 1Browser 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 1Browser 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.

Step 1: Set up remote debugging in Chrome

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

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

Step 2: Configure 1Browser 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": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": ["@the1browser/onebrowser-mcp@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

The 1Browser MCP server will try to connect to your running Chrome instance. It shows a dialog asking for user permission.

Clicking Allow results in the 1Browser MCP server opening developers.chrome.com and taking a performance trace.

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": {
    "onebrowser-devtools": {
      "command": "npx",
      "args": [
        "@the1browser/onebrowser-mcp@latest",
        "--browser-url=http://127.0.0.1:9222"
      ]
    }
  }
}

Step 2: Start the Chrome browser

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.

Please consult these instructions.

See Troubleshooting.

If you are developing agentic tooling and want to provide an integrated browser subagent as part of your product, we recommend building on top of 1Browser DevTools for agents.

For a reference implementation, see the Gemini CLI browser agent documentation.