Skip to content
Back to search

chrome-devtools-plugins

MarketplaceWorks with Claude CodeGitHub

Bundled plugins for actuating and debugging the Chrome browser.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 12 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/ChromeDevTools/chrome-devtools-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/ChromeDevTools/chrome-devtools-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/chromedevtools-chrome-devtools-mcp/badge.svg)](/listings/chromedevtools-chrome-devtools-mcp)

HTML

<a href="/listings/chromedevtools-chrome-devtools-mcp"><img src="/api/listings/chromedevtools-chrome-devtools-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Add the following config to your MCP client:

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

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

MCP Client configuration

For setup instructions specific to your editor or agent (e.g. Antigravity, Claude Code, Cursor, VS Code), please see our [Client Configurations Guide][client-configurations-guide].

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.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 17 lines
  1. {
  2. "name": "chrome-devtools-plugins",
  3. "version": "1.13.0",
  4. "description": "Bundled plugins for actuating and debugging the Chrome browser.",
  5. "repository": "https://github.com/ChromeDevTools/chrome-devtools-mcp",
  6. "owner": {
  7. "name": "Chrome DevTools Team",
  8. "email": "devtools-dev@chromium.org"
  9. },
  10. "plugins": [
  11. {
  12. "name": "chrome-devtools-mcp",
  13. "source": "./",
  14. "description": "Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer"
  15. }
  16. ]
  17. }
README.md · README · 198 lines
  1. # Chrome DevTools for agents
  2. [![npm chrome-devtools-mcp package](https://img.shields.io/npm/v/chrome-devtools-mcp.svg)](https://npmjs.org/package/chrome-devtools-mcp)
  3. Chrome DevTools for agents (`chrome-devtools-mcp`) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot)
  4. control and inspect a live Chrome browser. It is available as a
  5. Model-Context-Protocol (MCP) server and as a [CLI][cli]. Both give your AI
  6. coding assistant access to the full power of Chrome DevTools for reliable
  7. automation, in-depth debugging, and performance analysis.
  8. [Tool reference][tool-reference] | [CLI][cli] | [Skills][skills] | [Changelog][changelog] | [Contributing][contributing] | [Troubleshooting][troubleshooting] | [Design Principles][design-principles]
  9. ## Key features
  10. - **Get performance insights**: Uses [Chrome
  11. DevTools](https://github.com/ChromeDevTools/devtools-frontend) to record
  12. traces and extract actionable performance insights.
  13. - **Advanced browser debugging**: Analyze network requests, take screenshots and
  14. check browser console messages (with source-mapped stack traces).
  15. - **Reliable automation**. Uses
  16. [puppeteer](https://github.com/puppeteer/puppeteer) to automate actions in
  17. Chrome and automatically wait for action results.
  18. ## Disclaimers
  19. `chrome-devtools-mcp` exposes content of the browser instance to the MCP clients
  20. allowing them to inspect, debug, and modify any data in the browser or DevTools.
  21. Avoid sharing sensitive or personal information that you don't want to share with
  22. MCP clients.
  23. `chrome-devtools-mcp` officially supports Google Chrome and [Chrome for Testing](https://developer.chrome.com/blog/chrome-for-testing/) only.
  24. Other Chromium-based browsers may work, but this is not guaranteed, and you may encounter unexpected behavior. Use at your own discretion.
  25. We are committed to providing fixes and support for the latest version of [Extended Stable Chrome](https://chromiumdash.appspot.com/schedule).
  26. Performance tools may send trace URLs to the Google CrUX API to fetch real-user
  27. experience data. This helps provide a holistic performance picture by
  28. presenting field data alongside lab data. This data is collected by the [Chrome
  29. User Experience Report (CrUX)](https://developer.chrome.com/docs/crux). To disable
  30. this, run with the `--no-performance-crux` flag.
  31. ## **Usage statistics**
  32. Google collects usage statistics (such as tool invocation success rates, latency, and environment information) to improve the reliability and performance of Chrome DevTools MCP.
  33. Data collection is **enabled by default**. You can opt-out by passing the `--no-usage-statistics` flag when starting the server:
  34. ```json
  35. "args": ["-y", "chrome-devtools-mcp@latest", "--no-usage-statistics"]
  36. ```
  37. Google handles this data in accordance with the [Google Privacy Policy](https://policies.google.com/privacy).
  38. Google's collection of usage statistics for Chrome DevTools 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.
  39. Collection is disabled if `CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS` or `CI` env variables are set.
  40. ## Update checks
  41. By default, the server periodically checks the npm registry for updates and logs a notification when a newer version is available.
  42. You can disable these update checks by setting the `CHROME_DEVTOOLS_MCP_NO_UPDATE_CHECKS` environment variable.
  43. ## Requirements
  44. - [Node.js](https://nodejs.org/) [LTS](https://github.com/nodejs/Release#release-schedule) version.
  45. - [Chrome](https://www.google.com/chrome/) current stable version or newer.
  46. - [npm](https://www.npmjs.com/)
  47. ## Getting started
  48. Add the following config to your MCP client:
  49. ```json
  50. {
  51. "mcpServers": {
  52. "chrome-devtools": {
  53. "command": "npx",
  54. "args": ["-y", "chrome-devtools-mcp@latest"]
  55. }
  56. }
  57. }
  58. ```
  59. > [!NOTE]
  60. > Using `chrome-devtools-mcp@latest` ensures that your MCP client will always use the latest version of the Chrome DevTools MCP server.
  61. ### MCP Client configuration
  62. For setup instructions specific to your editor or agent (e.g. Antigravity, Claude Code, Cursor, VS Code), please see our [Client Configurations Guide][client-configurations-guide].
  63. ### Your first prompt
  64. Enter the following prompt in your MCP Client to check if everything is working:
  65. ```
  66. Check the performance of https://developers.chrome.com
  67. ```
  68. Your MCP client should open the browser and record a performance trace.
  69. > [!NOTE]
  70. > 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.
  71. ## CLI
  72. The package also includes the `chrome-devtools` CLI. Use it to control the browser from your terminal without MCP:
  73. ```sh
  74. npm i chrome-devtools-mcp@latest -g
  75. chrome-devtools navigate_page 1 --url "https://developers.chrome.com"
  76. chrome-devtools take_screenshot 1 --filePath screenshot.png
  77. chrome-devtools stop
  78. ```
  79. See the [CLI guide][cli] for all commands and options.
  80. ## Skills
  81. The package includes [skills](./skills) that teach your agent how to use Chrome DevTools:
  82. | Skill | Use it to |
  83. | --------------------------------------------------------- | ----------------------------------------------- |
  84. | [`chrome-devtools`](./skills/chrome-devtools) | Debug and automate pages with the MCP tools. |
  85. | [`chrome-devtools-cli`](./skills/chrome-devtools-cli) | Run the CLI and write shell scripts with it. |
  86. | [`a11y-debugging`](./skills/a11y-debugging) | Audit and fix accessibility issues. |
  87. | [`cookie-debugging`](./skills/cookie-debugging) | Debug cookies, sessions, and authentication. |
  88. | [`debug-optimize-lcp`](./skills/debug-optimize-lcp) | Debug and improve Largest Contentful Paint. |
  89. | [`memory-leak-debugging`](./skills/memory-leak-debugging) | Find and fix memory leaks. |
  90. | [`troubleshooting`](./skills/troubleshooting) | Fix connection problems between MCP and Chrome. |
  91. ### Install skills as a plugin
  92. A plugin installs the MCP server and all skills, including the CLI skill:
  93. - **Claude Code:** Run `/plugin marketplace add ChromeDevTools/chrome-devtools-mcp`, then `/plugin install chrome-devtools-mcp@chrome-devtools-plugins`.
  94. - **Copilot / VS Code:** Run **Chat: Install Plugin From Source** and enter `ChromeDevTools/chrome-devtools-mcp`.
  95. - **Gemini CLI:** Run `gemini extensions install --auto-update https://github.com/ChromeDevTools/chrome-devtools-mcp`.
  96. See the [Client Configurations Guide][client-configurations-guide] for more information.
  97. ### Install skills manually
  98. If your agent does not support plugins, copy the skill folders into the skills directory of your agent. The npm package contains the skills:
  99. ```sh
  100. npm i chrome-devtools-mcp@latest -g
  101. # Example for Claude Code. Use the skills directory of your agent.
  102. mkdir -p ~/.claude/skills
  103. cp -R "$(npm root -g)/chrome-devtools-mcp/skills/chrome-devtools-cli" ~/.claude/skills/
  104. ```
  105. > [!IMPORTANT]
  106. > The `chrome-devtools-cli` skill requires the CLI. Install the package globally before you use the skill.
  107. ### Keep skills up to date
  108. Skills describe the tools of a specific version. Update the skills each time you update the MCP server or the CLI. Outdated skills can tell your agent to use tools or parameters that changed.
  109. - **Plugins:** Use the update command of the plugin manager of your agent. The Gemini CLI command above enables automatic updates with `--auto-update`.
  110. - **Manual installs:** Update the package, then copy the skill folders again:
  111. ```sh
  112. npm i chrome-devtools-mcp@latest -g
  113. mkdir -p ~/.claude/skills
  114. cp -R "$(npm root -g)/chrome-devtools-mcp/skills/chrome-devtools-cli" ~/.claude/skills/
  115. ```
  116. ## Tools
  117. If you run into any issues, checkout our [troubleshooting guide][troubleshooting].
  118. See the full [Tool Reference][tool-reference] for a complete list of all supported MCP capabilities.
  119. ## Configuration
  120. Find the complete list of server parameters (e.g., `--headless`, `--isolated`, `--slim`) and how to configure WebSocket connections in the [Configuration Guide][configuration-guide].
  121. For basic browser tasks only, the `--slim` flag exposes a reduced set of tools. See the [Slim tool reference][slim-tool-reference].
  122. ## Advanced Usage
  123. For advanced features such as handling concurrent sessions, persistent user data directories, using a custom or non-standard browser path (`--executablePath`), connecting to a running Chrome instance instead of starting a new one, or debugging on Android, see our [Advanced Usage Guide][advanced-usage-guide].
  124. ## Integrating as a browser subagent
  125. 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 Chrome DevTools for agents.
  126. For a reference implementation, see the [Gemini CLI browser agent documentation](https://geminicli.com/docs/core/subagents/#browser-agent).
  127. [advanced-usage-guide]: ./docs/advanced-usage.md
  128. [changelog]: ./CHANGELOG.md
  129. [cli]: ./docs/cli.md
  130. [client-configurations-guide]: ./docs/client-configurations.md
  131. [configuration-guide]: ./docs/configuration.md
  132. [contributing]: ./CONTRIBUTING.md
  133. [design-principles]: ./docs/design-principles.md
  134. [skills]: #skills
  135. [slim-tool-reference]: ./docs/slim-tool-reference.md
  136. [tool-reference]: ./docs/tool-reference.md
  137. [troubleshooting]: ./docs/troubleshooting.md

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.