Skip to content
Download Longwave

Chrome DevTools

Chrome DevTools is an MCP server for inspecting a live Chrome session. The connected implementation exposes 29 tools for browser debugging, console output, network activity and performance work.

Add to Longwave Source

Install elsewhere

Install Chrome DevTools

Choose a harness. These instructions start the same local MCP server shown on this page.

Claude Code

Run this in your terminal. It adds a user-scoped server; use --scope project instead if it should apply only to the current project.

terminal 
claude mcp add --scope user --transport stdio chrome-devtools -- npx -y [email protected]

What it does

Chrome DevTools MCP connects an agent to Chrome's developer tooling. The agent can inspect the page it is debugging instead of relying only on the rendered screen.

  • Read console messages while a page is running.
  • Inspect network requests and responses.
  • Examine page structure, styles and browser state.
  • Collect performance information from a live Chrome session.
  • Use the exact tool arguments returned by the connected server.

Skills that ship with it

The MCP server gives the agent Chrome's tools. These skills give it the workflows: which tool to call first, which traces to record, and what the numbers mean. Each one names the MCP tools it expects. Longwave installs them with the server, and each name below opens the skill's source.

Available functions

click Clicks on the provided element

Arguments

dblClick
boolean Set to true for double clicks. Default is false.
includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
uid required
string The uid of an element on the page from the page content snapshot
close_page Closes the page by its index. The last open page cannot be closed.

Arguments

pageId required
number The ID of the page to close. Call list_pages to list pages.
drag Drag an element onto another element

Arguments

from_uid required
string The uid of the element to drag
includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
to_uid required
string The uid of the element to drop into
emulate Emulates various features on the target page.

Arguments

colorScheme
string Emulate the dark or the light mode. Set to "auto" to reset to the default. Allowed values: dark, light, auto
cpuThrottlingRate
number Represents the CPU slowdown factor. Omit or set the rate to 1 to disable throttling
extraHttpHeaders
string Extra 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 navigations until cleared. Pass an empty string to clear all extra headers.
geolocation
string Geolocation (`<latitude>,<longitude>`) to emulate. Latitude between -90 and 90. Longitude between -180 and 180. Omit to clear the geolocation override.
networkConditions
string Throttle network. Omit to disable throttling. Allowed values: Offline, Slow 3G, Fast 3G, Slow 4G, Fast 4G
pageId required
number Targets a specific page by ID.
userAgent
string User agent to emulate. Set to empty string to clear the user agent override.
viewport
string Emulate device viewports '<width>x<height>x<devicePixelRatio>[,mobile][,touch][,landscape]'. 'touch' and 'mobile' to emulate mobile devices. 'landscape' to emulate landscape mode.
evaluate_script Evaluate a JavaScript function inside the target page. Returns the response as JSON, so returned values have to be JSON-serializable.

Arguments

args
array An optional list of arguments to pass to the function.
dialogAction
string Handle dialogs while execution. "accept", "dismiss", or string for response of window.prompt. Defaults to accept.
filePath
string The absolute or relative path to a file to save the script output to. If omitted, the output is returned inline.
function required
string A JavaScript function declaration to be executed by the tool in the target page. Example without arguments: `() => document.title` or `async () => await fetch("example.com")`. Example with arguments: `(el) => el.innerText`
pageId required
number Targets a specific page by ID.
waitForStableDom
boolean Whether to wait for the DOM to settle. Pass false if the script only reads data. Defaults to true.
fill Type text into an input, text area or select an option from a <select> element.

Arguments

includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
uid required
string The uid of an element on the page from the page content snapshot
value required
string The value to fill in. "true" or "false" for checkboxes and toggles, "true" for radio buttons.
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.

Arguments

elements required
array Elements from snapshot to fill out.
includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
get_console_message Gets a console message by its ID. You can get all messages by calling list_console_messages.

Arguments

msgid required
number The msgid of a console message on the page from the listed console messages
pageId required
number Targets a specific page by ID.
get_network_request Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.

Arguments

pageId required
number Targets a specific page by ID.
reqid
number The reqid of the network request. If omitted returns the currently selected request in the DevTools Network panel.
requestFilePath
string The absolute or relative path to a .network-request file to save the request body to. If omitted, the body is returned inline.
responseFilePath
string The absolute or relative path to a .network-response file to save the response body to. If omitted, the body is returned inline.
handle_dialog If a browser dialog was opened, use this command to handle it

Arguments

action required
string Whether to dismiss or accept the dialog Allowed values: accept, dismiss
pageId required
number Targets a specific page by ID.
promptText
string Optional prompt text to enter into the dialog.
hover Hover over the provided element

Arguments

includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
uid required
string The uid of an element on the page from the page content snapshot
lighthouse_audit Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run performance_start_trace

Arguments

device
string Device to emulate. Allowed values: desktop, mobile Default: desktop
mode
string "navigation" reloads & audits. "snapshot" analyzes current state. Allowed values: navigation, snapshot Default: navigation
outputDirPath
string Directory for reports. If omitted, uses temporary files.
pageId required
number Targets a specific page by ID.
list_console_messages List all console messages for the target page since the last navigation.

Arguments

includePreservedMessages
boolean Set to true to return the preserved messages over the last 3 navigations. Default: false
includeStackTraces
boolean Set to true to include the stack trace for each message when available. Increases the response size. Default: false
pageId required
number Targets a specific page by ID.
pageIdx
integer Page number to return (0-based). When omitted, returns the first page.
pageSize
integer Maximum number of messages to return. When omitted, returns all messages.
serviceWorkerId
string Filter messages to only return messages of the specified service worker.
types
array Filter messages to only return messages of the specified resource types. When omitted or empty, returns all messages.
list_network_requests Lists the most recent requests for the target page since the last navigation.

Arguments

includePreservedRequests
boolean Set to true to return the preserved requests over the last 3 navigations. Default: false
pageId required
number Targets a specific page by ID.
pageIdx
integer Page number to return (0-based). When omitted, returns the first page.
pageSize
integer Maximum number of requests to return. When omitted, returns all requests.
resourceTypes
array Filter requests to only return requests of the specified resource types. When omitted or empty, returns all requests.
list_pages Get a list of pages open in the browser.
navigate_page Go to a URL, or back, forward, or reload. Use project URL if not specified otherwise.

Arguments

handleBeforeUnload
string Whether to auto accept or beforeunload dialogs triggered by this navigation. Default is accept. Allowed values: accept, dismiss
ignoreCache
boolean Whether to ignore cache on reload.
initScript
string A JavaScript script to be executed on each new document before any other scripts for the next navigation.
pageId required
number Targets a specific page by ID.
timeout
integer Maximum wait time in milliseconds. If set to 0, the default timeout will be used.
type
string Navigate the page by URL, back or forward in history, or reload. Allowed values: url, back, forward, reload
url
string Target URL (only type=url)
new_page Open a new tab and load a URL. Use project URL if not specified otherwise.

Arguments

background
boolean Whether to open the page in the background without bringing it to the front. Default is false (foreground).
isolatedContext
string If 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 isolated.
timeout
integer Maximum wait time in milliseconds. If set to 0, the default timeout will be used.
url required
string URL to load in a new page.
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.

Arguments

insightName required
string The name of the Insight you want more information on. For example: "DocumentLatency" or "LCPBreakdown"
insightSetId required
string The id for the specific insight set. Only use the ids given in the "Available insight sets" list.
pageId required
number Targets a specific page by ID.
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.

Arguments

autoStop
boolean Determines if the trace recording should be automatically stopped. Default: true
filePath
string The 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).
pageId required
number Targets a specific page by ID.
reload
boolean Determines if, once tracing has started, the target page should be automatically reloaded. Navigate the page to the right URL using the navigate_page tool BEFORE starting the trace if reload or autoStop is set to true. Default: true
performance_stop_trace Stop the active performance trace recording on the target webpage.

Arguments

filePath
string The 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).
pageId required
number Targets a specific page by ID.
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).

Arguments

includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
key required
string A key or a combination (e.g., "Enter", "Control+A", "Control++", "Control+Shift+R"). Modifiers: Control, Shift, Alt, Meta
pageId required
number Targets a specific page by ID.
resize_page Resizes the page's window so that the page has specified dimension

Arguments

height required
number Page height
pageId required
number Targets a specific page by ID.
width required
number Page width
select_page Select a page as a context for future tool calls.

Arguments

bringToFront
boolean Whether to focus the page and bring it to the top.
pageId required
number The ID of the page to select. Call list_pages to get available pages.
take_heapsnapshot Capture a heap snapshot of the target page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks.

Arguments

filePath required
string A path to a .heapsnapshot file to save the heapsnapshot to.
pageId required
number Targets a specific page by ID.
take_screenshot Take a screenshot of the page or element.

Arguments

filePath
string The absolute path, or a path relative to the current working directory, to save the screenshot to instead of attaching it to the response.
format
string Type of format to save the screenshot as. Default is "png" Allowed values: png, jpeg, webp Default: png
fullPage
boolean If set to true takes a screenshot of the full page instead of the currently visible viewport. Incompatible with uid.
pageId required
number Targets a specific page by ID.
quality
number Compression quality for JPEG and WebP formats (0-100). Higher values mean better quality but larger file sizes. Ignored for PNG format.
uid
string The uid of an element on the page from the page content snapshot. If omitted, takes a page screenshot.
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).

Arguments

filePath
string The absolute path, or a path relative to the current working directory, to save the snapshot to instead of attaching it to the response.
pageId required
number Targets a specific page by ID.
verbose
boolean Whether to include all possible information available in the full a11y tree. Default is false.
type_text Type text using keyboard into a previously focused input

Arguments

pageId required
number Targets a specific page by ID.
submitKey
string Optional key to press after typing. E.g., "Enter", "Tab", "Escape"
text required
string The text to type
upload_file Upload a file through a provided element.

Arguments

filePaths required
array One or more files paths to upload. File paths have to be local to the browser instance (not the MCP).
includeSnapshot
boolean Whether to include a snapshot in the response. Default is false.
pageId required
number Targets a specific page by ID.
uid required
string The uid of the file input element or an element that will open file chooser on the page from the page content snapshot
wait_for Wait for the specified text to appear on the selected page.

Arguments

pageId required
number Targets a specific page by ID.
text required
array Non-empty list of texts. Resolves when any value appears on the page.
timeout
integer Maximum wait time in milliseconds. If set to 0, the default timeout will be used.

Questions people ask

How do I install Chrome DevTools MCP?

Add the catalog-backed `chrome-devtools-mcp` package as a local MCP server, then start it from the client that will use Chrome. The server requires Node.js.

Which npm package does Chrome DevTools MCP use?

The integrated entry is backed by the published `chrome-devtools-mcp` package. The exact launch command for the page's current source appears in the installation controls.

How do I use Chrome DevTools MCP in Cursor?

Add the server to Cursor's MCP settings and start it with access to the Chrome session you want to inspect. Cursor Agent can then call the debugging functions returned during initialization.

Can Claude Code use Chrome DevTools MCP?

Yes. Add the local server to Claude Code's MCP configuration and start it with Node.js. Claude Code can use the functions after Chrome DevTools MCP connects.

Can Chrome DevTools MCP run in Docker?

The package can be started in a container, but the container still needs a Chrome instance and a DevTools connection. A container alone does not provide a browser session to inspect.

What is the difference between Chrome DevTools MCP and Playwright MCP?

Chrome DevTools MCP is for inspecting and debugging a live Chrome session. Playwright MCP is for driving browser interactions such as navigation, clicks and form input. Choose based on whether the task is debugging or browser control.

Give the agent the browser evidence.

Inspect the console, network and performance data without leaving the work session.

Download Longwave