Lets an AI coding agent control and inspect a live Chrome browser for automation, debugging, and performance analysis.
Also known as ChromeDevTools/chrome-devtools-mcp, chrome-devtools-mcp
- Stars
- 56,922
- Tools
- 33
- Downloads, 30 days
- —
- Latest version
- 1.13.0
- Last commit
- Nov 15, 2026
- License
- Apache-2.0
What is Chrome DevTools MCP?
Chrome DevTools lets an AI coding agent control and inspect a live Chrome browser for automation, debugging, and performance analysis. It exposes 33 tools, such as click, close_page, drag.
Summary generated from the project's README
About Chrome DevTools MCP server
Automating browser tasks and inspecting web performance from within an AI coding agent is what Chrome DevTools MCP enables. Developers using tools like Claude, Cursor, or Copilot can grant their assistants direct control over a live Google Chrome instance to perform debugging, automation, and analysis. The server connects to the browser via Puppeteer to execute actions and can be configured to run in various modes, including a slim version with a reduced toolset.
Setting up the server requires Node.js and a current stable version of Chrome. It can be integrated into MCP clients using npx or managed through a command-line interface for terminal-based control. The system provides specialized capabilities for tasks such as analyzing network requests, capturing screenshots, and examining console messages with source-mapped stack traces. It also integrates with the Google CrUX API to combine lab data with real-user experience metrics for a complete performance overview.
What you can do with it
- 1Analyze web performanceAsk your AI agent to evaluate how quickly a specific website loads and identify bottlenecks.
Written from the project's README. Every use case is checked against a quote from it.
How to install Chrome DevTools MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Chrome DevTools MCP in Claude Code
$ claude mcp add chrome-devtools-mcp -- npx -y chrome-devtools-mcpInstall Chrome DevTools MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"chrome-devtools-mcp": {
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
}Install Chrome DevTools MCP in VS Code
.vscode/mcp.json
{
"servers": {
"chrome-devtools-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
}Install Chrome DevTools MCP in VS Code CLI
$ code --add-mcp '{"name":"chrome-devtools-mcp","type":"stdio","command":"npx","args":["-y","chrome-devtools-mcp"]}'Install Chrome DevTools MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"chrome-devtools-mcp": {
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
}Install Chrome DevTools MCP in Codex
$ codex mcp add chrome-devtools-mcp -- npx -y chrome-devtools-mcpInstall Chrome DevTools MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.chrome-devtools-mcp] command = "npx" args = ["-y", "chrome-devtools-mcp"]
Install Chrome DevTools MCP in Gemini CLI
$ gemini mcp add -s user chrome-devtools-mcp npx -- -y chrome-devtools-mcpInstall Chrome DevTools MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"chrome-devtools-mcp": {
"command": "npx",
"args": [
"-y",
"chrome-devtools-mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for chrome-devtools-mcp 1.13.0 in an isolated container with no network and no keys. It answered and listed 33 tools.
Chrome DevTools MCP tools 33
Read from the server with tools/listclickActionClicks on the provided element
close_pageActionCloses the page by its index. The last open page cannot be closed.
dragActionDrag an element onto another element
emulateActionEmulates various features on the target page. Each call replaces all emulation settings (except extraHttpHeaders), so pass all desired settings in a single call.
evaluate_scriptActionEvaluate JavaScript inside the target page. The source can be provided inline or loaded from a local file. Returns the response as JSON, so returned values have to be JSON-serializable.
fillActionType text into an input, text area or select an option from a <select> element.
fill_formActionFill out multiple form elements (inputs, selects, checkboxes, radios) at once. ALWAYS prefer this tool over multiple individual 'fill' or 'click' calls when interacting with forms. It is significantly faster, more reliable, and reduces turn count. Example: Fill username, password, and check "Remember Me" in one call.
get_console_messageRead-onlyGets a console message by its ID. You can get all messages by calling list_console_messages.
get_css_stylesRead-onlyRetrieve matched CSS rules, inline styles (element.style), inherited styles, custom properties, and cascade wrappers (@layer, @media, @container, @scope) for an element identified by its UID. Rules are ordered from highest to lowest cascade precedence and include source line numbers (e.g. index:196). Active (winning) declarations have no prefix tag, while (losing) overridden declarations are prefixed with [overloaded]. Treat the output as authoritative and complete. Results are paginated (10 rules per page by default); use pageIdx to page through the remaining rules. Requires a UID from take_snapshot.
get_network_requestActionGets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel. Useful for inspecting request headers (including 'Cookie') and response headers (including 'Set-Cookie' and directives).
handle_dialogActionIf a browser dialog was opened, use this command to handle it
hoverActionHover over the provided element
| click | Clicks on the provided element | Action |
| close_page | Closes the page by its index. The last open page cannot be closed. | Action |
| drag | Drag an element onto another element | Action |
| emulate | Emulates various features on the target page. Each call replaces all emulation settings (except extraHttpHeaders), so pass all desired settings in a single call. | Action |
| evaluate_script | Evaluate JavaScript inside the target page. The source can be provided inline or loaded from a local file. Returns the response as JSON, so returned values have to be JSON-serializable. | Action |
| fill | Type text into an input, text area or select an option from a <select> element. | Action |
| fill_form | Fill out multiple form elements (inputs, selects, checkboxes, radios) at once. ALWAYS prefer this tool over multiple individual 'fill' or 'click' calls when interacting with forms. It is significantly faster, more reliable, and reduces turn count. Example: Fill username, password, and check "Remember Me" in one call. | Action |
| get_console_message | Gets a console message by its ID. You can get all messages by calling list_console_messages. | Read-only |
| get_css_styles | Retrieve matched CSS rules, inline styles (element.style), inherited styles, custom properties, and cascade wrappers (@layer, @media, @container, @scope) for an element identified by its UID. Rules are ordered from highest to lowest cascade precedence and include source line numbers (e.g. index:196). Active (winning) declarations have no prefix tag, while (losing) overridden declarations are prefixed with [overloaded]. Treat the output as authoritative and complete. Results are paginated (10 rules per page by default); use pageIdx to page through the remaining rules. Requires a UID from take_snapshot. | Read-only |
| get_network_request | Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel. Useful for inspecting request headers (including 'Cookie') and response headers (including 'Set-Cookie' and directives). | Action |
| handle_dialog | If a browser dialog was opened, use this command to handle it | Action |
| hover | Hover over the provided element | Action |
Show all 33 toolsShow fewer tools
lighthouse_auditActionGet Lighthouse scores, failing audits, and the DOM nodes they flag for accessibility, SEO, best practices, and agentic browsing. Full reports are saved to disk. This excludes performance. For performance audits, run performance_start_trace
list_console_messagesRead-onlyList all console messages for the target page since the last navigation.
list_network_requestsRead-onlyLists the most recent requests for the target page since the last navigation.
list_pagesRead-onlyGet a list of pages open in the browser.
navigate_pageActionGo to a URL, or back, forward, or reload. Use project URL if not specified otherwise.
new_pageActionOpen a new tab and load a URL. Use project URL if not specified otherwise.
performance_analyze_insightRead-onlyProvides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.
performance_start_traceActionStart a performance trace on the target webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed.
performance_stop_traceActionStop the active performance trace recording on the target webpage.
press_keyActionPress a key or key combination. Use this when other input methods like fill() cannot be used (e.g., keyboard shortcuts, navigation keys, or special key combinations). Note: On macOS, native <select> elements cannot be operated with ArrowDown/Enter via press_key; use fill() on the combobox or click() on the option instead.
resize_pageActionResizes the page's window so that the page has specified dimension
screencast_startActionStarts recording a screencast (video) of the target page.
screencast_stopActionStops the active screencast recording on the target page.
select_pageRead-onlySelect a page as a context for future tool calls.
set_logpointsActionSet the complete set of logpoints of the selected page: logpoints not in the list are removed, new ones are added, and an empty list removes all. A logpoint logs expressions to the console every time a line executes, without pausing or changing the source, like logpoints in the DevTools Sources panel. Locations are script URLs or original source files resolved through source maps (not available with --no-source-maps; scripts in workers and out-of-process iframes are not supported). A location in a generated script moves to its original source line when a source map covers it, and locations on the same line become one logpoint with the last expression. Output appears in list_console_messages; an expression that throws produces an error message without text. Logpoints survive reloads and navigations until removed or the page is closed. The response lists the resulting logpoints and where they are bound.
take_heapsnapshotActionCapture a heap snapshot of the target page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks.
take_screenshotActionTake a screenshot of the page or element.
take_snapshotActionTake a text snapshot of the target page based on the a11y tree. The snapshot lists page elements along with a unique identifier (uid). Always use the latest snapshot. Prefer taking a snapshot over taking a screenshot. The snapshot indicates the element selected in the DevTools Elements panel (if any).
type_textActionType text using keyboard into a previously focused input
upload_fileActionUpload a file through a provided element.
wait_forRead-onlyWait for the specified text to appear on the selected page. By default, hidden text is also matched. Set visible to true to wait until the matched text is visible.
| lighthouse_audit | Get Lighthouse scores, failing audits, and the DOM nodes they flag for accessibility, SEO, best practices, and agentic browsing. Full reports are saved to disk. This excludes performance. For performance audits, run performance_start_trace | Action |
| list_console_messages | List all console messages for the target page since the last navigation. | Read-only |
| list_network_requests | Lists the most recent requests for the target page since the last navigation. | Read-only |
| list_pages | Get a list of pages open in the browser. | Read-only |
| navigate_page | Go to a URL, or back, forward, or reload. Use project URL if not specified otherwise. | Action |
| new_page | Open a new tab and load a URL. Use project URL if not specified otherwise. | Action |
| performance_analyze_insight | Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording. | Read-only |
| performance_start_trace | Start a performance trace on the target webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed. | Action |
| performance_stop_trace | Stop the active performance trace recording on the target webpage. | Action |
| press_key | Press a key or key combination. Use this when other input methods like fill() cannot be used (e.g., keyboard shortcuts, navigation keys, or special key combinations). Note: On macOS, native <select> elements cannot be operated with ArrowDown/Enter via press_key; use fill() on the combobox or click() on the option instead. | Action |
| resize_page | Resizes the page's window so that the page has specified dimension | Action |
| screencast_start | Starts recording a screencast (video) of the target page. | Action |
| screencast_stop | Stops the active screencast recording on the target page. | Action |
| select_page | Select a page as a context for future tool calls. | Read-only |
| set_logpoints | Set the complete set of logpoints of the selected page: logpoints not in the list are removed, new ones are added, and an empty list removes all. A logpoint logs expressions to the console every time a line executes, without pausing or changing the source, like logpoints in the DevTools Sources panel. Locations are script URLs or original source files resolved through source maps (not available with --no-source-maps; scripts in workers and out-of-process iframes are not supported). A location in a generated script moves to its original source line when a source map covers it, and locations on the same line become one logpoint with the last expression. Output appears in list_console_messages; an expression that throws produces an error message without text. Logpoints survive reloads and navigations until removed or the page is closed. The response lists the resulting logpoints and where they are bound. | Action |
| take_heapsnapshot | Capture a heap snapshot of the target page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks. | Action |
| take_screenshot | Take a screenshot of the page or element. | Action |
| take_snapshot | Take a text snapshot of the target page based on the a11y tree. The snapshot lists page elements along with a unique identifier (uid). Always use the latest snapshot. Prefer taking a snapshot over taking a screenshot. The snapshot indicates the element selected in the DevTools Elements panel (if any). | Action |
| type_text | Type text using keyboard into a previously focused input | Action |
| upload_file | Upload a file through a provided element. | Action |
| wait_for | Wait for the specified text to appear on the selected page. By default, hidden text is also matched. Set visible to true to wait until the matched text is visible. | Read-only |
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablechromedevtools/chrome-devtools-mcp is public and reachablegithub.com/chromedevtools/chrome-devtools-mcp ↗Pass
- Package names this repository as its sourcechrome-devtools-mcp names chromedevtools/chrome-devtools-mcp as sourcenpmjs.com/package/chrome-devtools-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for chrome-devtools-mcpnpmjs.com/package/chrome-devtools-mcp/v/1.13.0#provenance ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-15github.com/chromedevtools/chrome-devtools-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from chrome-devtools-mcpPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model33 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubChrome DevTools for agents
Chrome DevTools for agents (chrome-devtools-mcp) lets your coding agent (such as Antigravity, Claude, Cursor or Copilot)
control and inspect a live Chrome browser. It is available as a
Model-Context-Protocol (MCP) server and as a CLI. Both give your AI
coding assistant access to the full power of Chrome DevTools for reliable
automation, in-depth debugging, and performance analysis.
Tool reference | CLI | Skills | 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
Google collects usage statistics (such as tool invocation success rates, latency, and environment information) to improve the reliability and performance of Chrome DevTools MCP.
Data collection is enabled by default. You can opt-out by passing the --no-usage-statistics flag when starting the server:
"args": ["-y", "chrome-devtools-mcp@latest", "--no-usage-statistics"]
Google handles this data in accordance with the Google Privacy Policy.
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.
Collection is disabled if CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS or CI env variables are set.
Update checks
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.
Requirements
Getting started
Add the following config to your MCP client:
{
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest"]
}
}
}
[!NOTE] Using
chrome-devtools-mcp@latestensures 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.
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.
CLI
The package also includes the chrome-devtools CLI. Use it to control the browser from your terminal without MCP:
npm i chrome-devtools-mcp@latest -g
chrome-devtools navigate_page 1 --url "https://developers.chrome.com"
chrome-devtools take_screenshot 1 --filePath screenshot.png
chrome-devtools stop
See the CLI guide for all commands and options.
Skills
The package includes skills that teach your agent how to use Chrome DevTools:
| Skill | Use it to |
|---|---|
chrome-devtools |
Debug and automate pages with the MCP tools. |
chrome-devtools-cli |
Run the CLI and write shell scripts with it. |
a11y-debugging |
Audit and fix accessibility issues. |
cookie-debugging |
Debug cookies, sessions, and authentication. |
debug-optimize-lcp |
Debug and improve Largest Contentful Paint. |
memory-leak-debugging |
Find and fix memory leaks. |
troubleshooting |
Fix connection problems between MCP and Chrome. |
Install skills as a plugin
A plugin installs the MCP server and all skills, including the CLI skill:
- Claude Code: Run
/plugin marketplace add ChromeDevTools/chrome-devtools-mcp, then/plugin install chrome-devtools-mcp@chrome-devtools-plugins. - Copilot / VS Code: Run Chat: Install Plugin From Source and enter
ChromeDevTools/chrome-devtools-mcp. - Gemini CLI: Run
gemini extensions install --auto-update https://github.com/ChromeDevTools/chrome-devtools-mcp.
See the Client Configurations Guide for more information.
Install skills manually
If your agent does not support plugins, copy the skill folders into the skills directory of your agent. The npm package contains the skills:
npm i chrome-devtools-mcp@latest -g
# Example for Claude Code. Use the skills directory of your agent.
mkdir -p ~/.claude/skills
cp -R "$(npm root -g)/chrome-devtools-mcp/skills/chrome-devtools-cli" ~/.claude/skills/
[!IMPORTANT] The
chrome-devtools-cliskill requires the CLI. Install the package globally before you use the skill.
Keep skills up to date
Skills describe the tools of a specific version. Update the skills each time you update the MCP server or the CLI. Outdated skills can tell your agent to use tools or parameters that changed.
- Plugins: Use the update command of the plugin manager of your agent. The Gemini CLI command above enables automatic updates with
--auto-update. - Manual installs: Update the package, then copy the skill folders again:
npm i chrome-devtools-mcp@latest -g
mkdir -p ~/.claude/skills
cp -R "$(npm root -g)/chrome-devtools-mcp/skills/chrome-devtools-cli" ~/.claude/skills/
Tools
If you run into any issues, checkout our troubleshooting guide. See the full Tool Reference for a complete list of all supported MCP capabilities.
Configuration
Find the complete list of server parameters (e.g., --headless, --isolated, --slim) and how to configure WebSocket connections in the Configuration Guide.
For basic browser tasks only, the --slim flag exposes a reduced set of tools. See the Slim tool reference.
Advanced Usage
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.
Integrating as a browser subagent
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.
For a reference implementation, see the Gemini CLI browser agent documentation.
Chrome DevTools MCP questions
How do I add Chrome DevTools MCP to Claude Code?
Run claude mcp add chrome-devtools-mcp -- npx -y chrome-devtools-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Chrome DevTools MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Chrome DevTools MCP provide?
It exposes 33 tools, including click, close_page, drag, emulate, evaluate_script.
What can an AI agent do with the Chrome DevTools MCP server?
It can control and inspect a live Chrome browser, including recording performance traces, analyzing network requests, taking screenshots, and checking console messages.
Which browsers does chrome-devtools-mcp support?
It officially supports Google Chrome and Chrome for Testing; other Chromium-based browsers may work but are not guaranteed.
How do I install the Chrome DevTools MCP server?
Add an MCP client config entry that runs npx with the chrome-devtools-mcp@latest package.
Does chrome-devtools-mcp collect usage statistics?
Yes, Google collects usage statistics by default; you can opt out with the --no-usage-statistics flag or the CHROME_DEVTOOLS_MCP_NO_USAGE_STATISTICS environment variable.
What are the requirements to run the server?
You need a Node.js LTS version, a current stable Chrome version or newer, and npm.