Summary
The Chrome DevTools MCP server enables AI coding agents to control and inspect live Chrome browser instances through the Model Context Protocol, providing tools for performance analysis, advanced debugging, and reliable automation. It offers capabilities including performance trace recording and analysis, network request inspection, screenshot capture, console message analysis with source mapping, and browser action automation via Puppeteer. The server solves the problem of giving AI assistants direct access to Chrome DevTools functionality for in-depth debugging, performance optimization, and reliable browser automation tasks.
Install to Claude Code
verifiedclaude mcp add chrome-devtools-mcp -- npx -y chrome-devtools-mcpRun in your terminal. Replace YOUR_* placeholders with real values; add --scope user to install for every project.
Review the command, arguments, and environment values before installing — MCP servers run with your local permissions.
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Tools
Verified live against the running server on Jun 10, 2026.
verified live29 tools
clickClicks on the provided element3 params
Clicks on the provided element
Parameters* required
dblClickbooleanSet to true for double clicks. Default is false.
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
uid*stringThe uid of an element on the page from the page content snapshot
close_pageCloses the page by its index. The last open page cannot be closed.1 params
Closes the page by its index. The last open page cannot be closed.
Parameters* required
pageId*numberThe ID of the page to close. Call list_pages to list pages.
dragDrag an element onto another element3 params
Drag an element onto another element
Parameters* required
from_uid*stringThe uid of the element to drag
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
to_uid*stringThe uid of the element to drop into
emulateEmulates various features on the selected page.7 params
Emulates various features on the selected page.
Parameters* required
colorSchemestringEmulate the dark or the light mode. Set to "auto" to reset to the default.one of
dark · light · autocpuThrottlingRatenumberRepresents the CPU slowdown factor. Omit or set the rate to 1 to disable throttling
extraHttpHeadersstringExtra HTTP headers as a JSON string object, e.g. {"X-Custom": "value", "Authorization": "Bearer token"}. Headers are included into every HTTP request originating from the page and persist across na...
geolocationstringGeolocation (`<latitude>,<longitude>`) to emulate. Latitude between -90 and 90. Longitude between -180 and 180. Omit to clear the geolocation override.
networkConditionsstringThrottle network. Omit to disable throttling.one of
Offline · Slow 3G · Fast 3G · Slow 4G · Fast 4GuserAgentstringUser agent to emulate. Set to empty string to clear the user agent override.
viewportstringEmulate device viewports '<width>x<height>x<devicePixelRatio>[,mobile][,touch][,landscape]'. 'touch' and 'mobile' to emulate mobile devices. 'landscape' to emulate landscape mode.
evaluate_scriptEvaluate a JavaScript function inside the currently selected page. Returns the response as JSON, so returned values have to be JSON-serializable.4 params
Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON, so returned values have to be JSON-serializable.
Parameters* required
argsarrayAn optional list of arguments to pass to the function.
dialogActionstringHandle dialogs while execution. "accept", "dismiss", or string for response of window.prompt. Defaults to accept.
filePathstringThe absolute or relative path to a file to save the script output to. If omitted, the output is returned inline.
function*stringA JavaScript function declaration to be executed by the tool in the currently selected page.
Example without arguments: `() => {
return document.title
}` or `async () => {
return await fetch("e...
fillType text into an input, text area or select an option from a <select> element.3 params
Type text into an input, text area or select an option from a <select> element.
Parameters* required
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
uid*stringThe uid of an element on the page from the page content snapshot
value*stringThe value to fill in. "true" or "false" for checkboxes and toggles, "true" for radio buttons.
fill_formFill 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, passw...2 params
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, passw...
Parameters* required
elements*arrayElements from snapshot to fill out.
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
get_console_messageGets a console message by its ID. You can get all messages by calling list_console_messages.1 params
Gets a console message by its ID. You can get all messages by calling list_console_messages.
Parameters* required
msgid*numberThe msgid of a console message on the page from the listed console messages
get_network_requestGets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.3 params
Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.
Parameters* required
reqidnumberThe reqid of the network request. If omitted returns the currently selected request in the DevTools Network panel.
requestFilePathstringThe absolute or relative path to a .network-request file to save the request body to. If omitted, the body is returned inline.
responseFilePathstringThe absolute or relative path to a .network-response file to save the response body to. If omitted, the body is returned inline.
handle_dialogIf a browser dialog was opened, use this command to handle it2 params
If a browser dialog was opened, use this command to handle it
Parameters* required
action*stringWhether to dismiss or accept the dialogone of
accept · dismisspromptTextstringOptional prompt text to enter into the dialog.
hoverHover over the provided element2 params
Hover over the provided element
Parameters* required
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
uid*stringThe uid of an element on the page from the page content snapshot
lighthouse_auditGet Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run performance_start_trace3 params
Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run performance_start_trace
Parameters* required
devicestringDevice to emulate.one of
desktop · mobiledefault: desktopmodestring"navigation" reloads & audits. "snapshot" analyzes current state.one of
navigation · snapshotdefault: navigationoutputDirPathstringDirectory for reports. If omitted, uses temporary files.
list_console_messagesList all console messages for the currently selected page since the last navigation.5 params
List all console messages for the currently selected page since the last navigation.
Parameters* required
includePreservedMessagesbooleanSet to true to return the preserved messages over the last 3 navigations.default: false
pageIdxintegerPage number to return (0-based). When omitted, returns the first page.
pageSizeintegerMaximum number of messages to return. When omitted, returns all messages.
serviceWorkerIdstringFilter messages to only return messages of the specified service worker.
typesarrayFilter messages to only return messages of the specified resource types. When omitted or empty, returns all messages.
list_network_requestsList all requests for the currently selected page since the last navigation.4 params
List all requests for the currently selected page since the last navigation.
Parameters* required
includePreservedRequestsbooleanSet to true to return the preserved requests over the last 3 navigations.default: false
pageIdxintegerPage number to return (0-based). When omitted, returns the first page.
pageSizeintegerMaximum number of requests to return. When omitted, returns all requests.
resourceTypesarrayFilter requests to only return requests of the specified resource types. When omitted or empty, returns all requests.
list_pagesGet a list of pages open in the browser.
Get a list of pages open in the browser.
No parameters — call it with no arguments.
navigate_pageGo to a URL, or back, forward, or reload. Use project URL if not specified otherwise.6 params
Go to a URL, or back, forward, or reload. Use project URL if not specified otherwise.
Parameters* required
handleBeforeUnloadstringWhether to auto accept or beforeunload dialogs triggered by this navigation. Default is accept.one of
accept · declineignoreCachebooleanWhether to ignore cache on reload.
initScriptstringA JavaScript script to be executed on each new document before any other scripts for the next navigation.
timeoutintegerMaximum wait time in milliseconds. If set to 0, the default timeout will be used.
typestringNavigate the page by URL, back or forward in history, or reload.one of
url · back · forward · reloadurlstringTarget URL (only type=url)
new_pageOpen a new tab and load a URL. Use project URL if not specified otherwise.4 params
Open a new tab and load a URL. Use project URL if not specified otherwise.
Parameters* required
backgroundbooleanWhether to open the page in the background without bringing it to the front. Default is false (foreground).
isolatedContextstringIf specified, the page is created in an isolated browser context with the given name. Pages in the same browser context share cookies and storage. Pages in different browser contexts are fully isol...
timeoutintegerMaximum wait time in milliseconds. If set to 0, the default timeout will be used.
url*stringURL to load in a new page.
performance_analyze_insightProvides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.2 params
Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.
Parameters* required
insightName*stringThe name of the Insight you want more information on. For example: "DocumentLatency" or "LCPBreakdown"
insightSetId*stringThe id for the specific insight set. Only use the ids given in the "Available insight sets" list.
performance_start_traceStart a performance trace on the selected webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed.3 params
Start a performance trace on the selected webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed.
Parameters* required
autoStopbooleanDetermines if the trace recording should be automatically stopped.default: true
filePathstringThe absolute file path, or a file path relative to the current working directory, to save the raw trace data. For example, trace.json.gz (compressed) or trace.json (uncompressed).
reloadbooleanDetermines if, once tracing has started, the current selected page should be automatically reloaded. Navigate the page to the right URL using the navigate_page tool BEFORE starting the trace if rel...default: true
performance_stop_traceStop the active performance trace recording on the selected webpage.1 params
Stop the active performance trace recording on the selected webpage.
Parameters* required
filePathstringThe absolute file path, or a file path relative to the current working directory, to save the raw trace data. For example, trace.json.gz (compressed) or trace.json (uncompressed).
press_keyPress 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).2 params
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).
Parameters* required
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
key*stringA key or a combination (e.g., "Enter", "Control+A", "Control++", "Control+Shift+R"). Modifiers: Control, Shift, Alt, Meta
resize_pageResizes the selected page's window so that the page has specified dimension2 params
Resizes the selected page's window so that the page has specified dimension
Parameters* required
height*numberPage height
width*numberPage width
select_pageSelect a page as a context for future tool calls.2 params
Select a page as a context for future tool calls.
Parameters* required
bringToFrontbooleanWhether to focus the page and bring it to the top.
pageId*numberThe ID of the page to select. Call list_pages to get available pages.
take_heapsnapshotCapture a heap snapshot of the currently selected page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks.1 params
Capture a heap snapshot of the currently selected page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks.
Parameters* required
filePath*stringA path to a .heapsnapshot file to save the heapsnapshot to.
take_screenshotTake a screenshot of the page or element.5 params
Take a screenshot of the page or element.
Parameters* required
filePathstringThe absolute path, or a path relative to the current working directory, to save the screenshot to instead of attaching it to the response.
formatstringType of format to save the screenshot as. Default is "png"one of
png · jpeg · webpdefault: pngfullPagebooleanIf set to true takes a screenshot of the full page instead of the currently visible viewport. Incompatible with uid.
qualitynumberCompression quality for JPEG and WebP formats (0-100). Higher values mean better quality but larger file sizes. Ignored for PNG format.
uidstringThe uid of an element on the page from the page content snapshot. If omitted, takes a page screenshot.
take_snapshotTake a text snapshot of the currently selected 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...2 params
Take a text snapshot of the currently selected 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...
Parameters* required
filePathstringThe absolute path, or a path relative to the current working directory, to save the snapshot to instead of attaching it to the response.
verbosebooleanWhether to include all possible information available in the full a11y tree. Default is false.
type_textType text using keyboard into a previously focused input2 params
Type text using keyboard into a previously focused input
Parameters* required
submitKeystringOptional key to press after typing. E.g., "Enter", "Tab", "Escape"
text*stringThe text to type
upload_fileUpload a file through a provided element.3 params
Upload a file through a provided element.
Parameters* required
filePath*stringThe local path of the file to upload
includeSnapshotbooleanWhether to include a snapshot in the response. Default is false.
uid*stringThe uid of the file input element or an element that will open file chooser on the page from the page content snapshot
wait_forWait for the specified text to appear on the selected page.2 params
Wait for the specified text to appear on the selected page.
Parameters* required
text*arrayNon-empty list of texts. Resolves when any value appears on the page.
timeoutintegerMaximum wait time in milliseconds. If set to 0, the default timeout will be used.
Chrome 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 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
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.
If you are interested in doing only basic browser tasks, use the --slim mode:
{
"mcpServers": {
"chrome-devtools": {
"command": "npx",
"args": ["-y", "chrome-devtools-mcp@latest", "--slim", "--headless"]
}
}
}
See Slim tool reference.
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.
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.
Advanced Usage
For advanced features such as handling concurrent sessions, persistent user data directories, 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.
Featured
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Categories
Registryactive
Packagechrome-devtools-mcp
TransportSTDIO
Tools verifiedJun 10, 2026
UpdatedJun 8, 2026
