mcp server
Chrome DevTools MCP
MCP server for Chrome DevTools
Description as published by the maintainer. Source
- version 1.6.0
- active
active — Most recent push to the repository was 2026-08-06.
What this server can do
29 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
click(uid, dblClick, includeSnapshot)- Clicks on the provided element Required: uid.
close_page(pageId)- Closes the page by its index. The last open page cannot be closed. Required: pageId.
drag(to_uid, from_uid, includeSnapshot)- Drag an element onto another element Required: from_uid, to_uid.
emulate(viewport, userAgent, colorScheme, geolocation, extraHttpHeaders, cpuThrottlingRate, networkConditions)- Emulates various features on the selected page.
evaluate_script(args, filePath, function, dialogAction)- Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON, so returned values have to be JSON-serializable. Required: function.
fill(uid, value, includeSnapshot)- Type text into an input, text area or select an option from a <select> element. Required: uid, value.
fill_form(elements, includeSnapshot)- 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. Required: elements.
get_console_message(msgid)- Gets a console message by its ID. You can get all messages by calling list_console_messages. Required: msgid.
get_network_request(reqid, requestFilePath, responseFilePath)- Gets a network request by an optional reqid, if omitted returns the currently selected request in the DevTools Network panel.
handle_dialog(action, promptText)- If a browser dialog was opened, use this command to handle it Required: action.
hover(uid, includeSnapshot)- Hover over the provided element Required: uid.
lighthouse_audit(mode, device, outputDirPath)- Get Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run performance_start_trace
list_console_messages(types, pageIdx, pageSize, serviceWorkerId, includePreservedMessages)- List all console messages for the currently selected page since the last navigation.
list_network_requests(pageIdx, pageSize, resourceTypes, includePreservedRequests)- List all requests for the currently selected page since the last navigation.
list_pages- Get a list of pages open in the browser.
navigate_page(url, type, timeout, initScript, ignoreCache, handleBeforeUnload)- Go to a URL, or back, forward, or reload. Use project URL if not specified otherwise.
new_page(url, timeout, background, isolatedContext)- Open a new tab and load a URL. Use project URL if not specified otherwise. Required: url.
performance_analyze_insight(insightName, insightSetId)- Provides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording. Required: insightSetId, insightName.
performance_start_trace(reload, autoStop, filePath)- 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.
performance_stop_trace(filePath)- Stop the active performance trace recording on the selected webpage.
press_key(key, includeSnapshot)- 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). Required: key.
resize_page(width, height)- Resizes the selected page's window so that the page has specified dimension Required: width, height.
select_page(pageId, bringToFront)- Select a page as a context for future tool calls. Required: pageId.
take_heapsnapshot(filePath)- Capture a heap snapshot of the currently selected page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks. Required: filePath.
take_screenshot(uid, format, quality, filePath, fullPage)- Take a screenshot of the page or element.
take_snapshot(verbose, filePath)- 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 the DevTools Elements panel (if any).
type_text(text, submitKey)- Type text using keyboard into a previously focused input Required: text.
upload_file(uid, filePath, includeSnapshot)- Upload a file through a provided element. Required: uid, filePath.
wait_for(text, timeout)- Wait for the specified text to appear on the selected page. Required: text.
Last successful function declaration observed on
.
Source: pkg:npm/chrome-devtools-mcp. We list what the server declared;
we do not call any of these functions.
Endpoint status observed on
.
Source: pkg:npm/chrome-devtools-mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 48,641 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-06 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 119 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.6.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-14 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | Apache-2.0 | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-14 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 29 tools | Number of functions the server declared when started and asked to list them. It says what the server offers an agent, not how well any of it works. | as of probe | npm |
|
| mcp endpoint status | ok | The server listed 29 functions when asked. | as of probe | npm |
|
| package install scripts | prepare | This package runs its own code during installation (prepare), before you ever start it. That is normal for many packages and is also where npm supply-chain attacks operate. We installed it with those scripts disabled. | as of probe | npm |
Where to get it
Related, by what their authors tagged them
-
PWA Debug Layer
— last commit 2026-06-26, shares chrome-devtools
Debug PWAs in your real browser via MCP: service-worker, cache, installability & framework state.
-
ai.smithery/browserbasehq-mcp-browserbase
— archived, last commit 2026-07-20, shares browser, chrome, puppeteer
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
-
io.github.browserbase/mcp-server-browserbase
— archived, last commit 2026-07-20, shares browser, chrome, puppeteer
MCP server for AI web browser automation using Browserbase and Stagehand
-
io.github.browser-gateway/browser-gateway
— last commit 2026-08-04, shares browser, puppeteer
AI browser tools with Chrome CDP. Navigate, screenshot, interact. Multi-provider failover.
-
AIR SDK
— last commit 2026-04-10, shares puppeteer
Collective intelligence for browser automation agents. Site capabilities, selectors, and extraction.
-
io.github.Custodia-Admin/pagebolt
— last commit 2026-08-06, shares puppeteer
Screenshots, PDFs, OG images, page inspection, and narrated video recording for Claude and Cursor.
-
io.github.dominion525/familiar-mcp
— last commit 2026-06-25, shares chrome
MCP server that drives the user's real macOS Chrome via AppleScript. 32 tools.
-
Pagerunner — The Browser Layer That Learns
— last commit 2026-08-01, shares chrome
Real Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist
-
io.github.fastslack/e2e-runner
— last commit 2026-06-08, shares puppeteer
JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.
-
Scout
— last commit 2026-08-03, shares chrome
Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.
These share tags the maintainers applied themselves, such as chrome-devtools, browser, chrome, puppeteer. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: browser, chrome, chrome-devtools, debugging, devtools, mcp, mcp-server, puppeteer.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json