← MCP servers · chromedevtools

Chrome DevTools

SAFEgrade B · trust 84/100

Chrome DevTools for coding agents

browserchromechrome devtoolsdebuggingdevtoolsmcpmcp serverpuppeteer

Overview

From the repository's own README, as read at the audited commit.

# Chrome DevTools for agents[![npm chrome-devtools-mcp package](https://img.shields.io/npm/v/chrome-devtools-mcp.svg)](https://npmjs.org/package/chrome-devtools-mcp)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 ofChrome DevTools for reliable automation, in-depth debugging, and performance analysis.A [CLI][cli] is also provided for use without MCP.[Tool reference][tool-reference] | [Changelog][changelog] | [Contributing][contributing] | [Troubleshooting][troubleshooting] | [Design Principles][design-principles]## Key features- **Get performance insights**: Uses [Chrome  DevTools](https://github.com/ChromeDevTools/devtools-frontend) 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](https://github.com/puppeteer/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 clientsallowing 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 withMCP clients.`chrome-devtools-mcp` officially supports Google Chrome and [Chrome for Testing](https://developer.chrome.com/blog/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](https://chromiumdash.appspot.com/schedule).Performance tools may send trace URLs to the Google CrUX API to fetch real-userex

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)
claude mcp add chrome-devtools-mcp -- npx -y [email protected]

Exposed tools (84) 70 read · 12 write · 2 destructive

Blast radius: 2 tools can delete or overwrite. An agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
3pDeveloperToolreadA test tool
clickreadClicks on the provided element
click_atreadClicks at the provided coordinates
close_heapsnapshotreadCloses a previously loaded memory heapsnapshot, freeing its memory.
close_pagereadCloses the page by its index. The last open page cannot be closed.
compare_heapsnapshotsreadLoads two memory heapsnapshots and returns the comparison. If classIndex is provided, returns detailed diff for that class, otherwise returns summary diff.
disabled_toolreadA disabled tool
dragreadDrag an element onto another element
emulatereadEmulates various features on the target page.
enum_toolreadtest description
evaluatereadEvaluates a JavaScript script
evaluate_scriptreadEvaluate a JavaScript function inside the target page${cliArgs?.categoryExtensions ?
execute_3p_developer_toolwriteExecutes a tool exposed by the page.
execute_webmcp_toolwriteExecutes a WebMCP tool exposed by the page.
file_toolreadA tool requiring file validation
fillreadType text into an input, text area or select an option from a <select> element.
fill_formreadFill out multiple form elements (inputs, selects, checkboxes, radios) at once. ALWAYS prefer this tool over multiple individual
get_console_messagereadGets a console message by its ID. You can get all messages by calling ${LIST_CONSOLE_MESSAGES_TOOL_NAME}.
get_devtools_commentsreadRetrieve user comments from the DevTools window for the page.
get_heapsnapshot_class_nodesreadLoads a memory heapsnapshot and returns instances of a specific class with their IDs.
get_heapsnapshot_detailsreadLoads a memory heapsnapshot and returns all available information including statistics, static data, and aggregated node information. Supports pagination for aggregates.
get_heapsnapshot_dominatorsreadLoads a memory heapsnapshot and returns the dominator chain for a specific node ID. This helps to identify which objects are keeping the target node alive.
get_heapsnapshot_duplicate_stringsreadLoads a memory heapsnapshot and returns duplicate strings grouped by their value.
get_heapsnapshot_edgesreadLoads a memory heapsnapshot and returns outgoing edges (references) for a specific node ID.
get_heapsnapshot_object_detailsreadLoads a memory heapsnapshot and returns detailed information about a specific object by its node ID, including size, type, distance, and DOM detachedness.
get_heapsnapshot_retainersreadLoads a memory heapsnapshot and returns retainers for a specific node ID.
get_heapsnapshot_retaining_pathsreadLoads a memory heapsnapshot and returns retaining paths for a specific node ID. This helps to understand why a node is not being garbage collected.
get_heapsnapshot_summaryreadLoads a memory heapsnapshot and returns snapshot summary stats, including native contexts and their sizes, and retained by context summary.
get_network_requestreadGets 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
get_os_app_statereadReturns the OS integration state (badge count and registered file
get_tab_idreadGet the tab ID of the page
global_toolreadA global tool
group-1readdesc-1
group-2readdesc-2
handle_dialogreadIf a browser dialog was opened, use this command to handle it
hoverreadHover over the provided element
hybrid_toolreadA tool with both schema file verifications
install_extensionwriteInstalls a Chrome extension from the given path.
install_pwawriteInstalls a Progressive Web App (PWA) identified by its manifest ID.
install_pwa_toolwritePWA tool with local-only file verification
launch_pwareadLaunches an installed Progressive Web App using its saved display mode.
lenient_toolreadA tool with a required argument
lighthouse_auditreadGet Lighthouse score and reports for accessibility, SEO, best practices, and agentic browsing. This excludes performance. For performance audits, run ${startTrace.name}
list_3p_developer_toolsreadLists all third-party developer tools the page exposes for providing runtime information.Third-party developer tools can be called via the
list_extensionsreadLists all the Chrome extensions installed in the browser. This includes their name, ID, version, and enabled status.
list_network_requestsreadLists the most recent requests for the target page since the last navigation.
list_pagesreadGet a list of pages${args?.categoryExtensions ?
list_webmcp_toolsreadLists all WebMCP tools the page exposes.
myToolreadDoes something
navigatereadLoads a URL
navigate_pagereadGo to a URL, or back, forward, or reload. Use project URL if not specified otherwise.
new_pagereadOpen a new tab and load a URL. Use project URL if not specified otherwise.
open_devtoolsreadOpen a DevTools window for the selected page.
page_file_toolreadA page scoped tool with file verification
page_toolreadA page scoped tool
performance_analyze_insightreadProvides more detailed information on a specific Performance Insight of an insight set that was highlighted in the results of a trace recording.
performance_start_tracewriteStart 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_tracewriteStop the active performance trace recording on the target webpage.
press_keyreadPress 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).
query_heapsnapshot_objectsreadLoads a memory heapsnapshot and queries objects matching specific filters (className, propertyName, nodeType, retainedSize, selfSize, isDetached, sortBy).
reload_extensionreadReloads an unpacked Chrome extension by its ID.
remote_file_toolreadA tool with remote-only file verification
resize_pagereadResizes the page
resolve_devtools_commentreadAppend an agent reply to a DevTools comment thread and mark it as resolved.
reveal_in_devtoolsreadNavigate DevTools to a specified panel and highlight a target DOM node or network request. The parameters uid and reqid are mutually exclusive.
screencast_startwriteStarts recording a screencast (video) of the target page in specified format.
screencast_stopwriteStops the active screencast recording on the target page.
screenshotreadTakes a screenshot
select_pagereadSelect a page as a context for future tool calls.
take_heapsnapshotreadCapture a heap snapshot of the target page. Use to analyze the memory distribution of JavaScript objects and debug memory leaks.
take_screenshotreadTake a screenshot of the page or element.
test-groupreadtest description
test-toolreadtest tool description
test_toolreadA test tool
tool-1readtool-1-desc
tool-2readtool-2-desc
trigger_extension_actionwriteTriggers the default action of an extension by its ID.
type_textreadType text using keyboard into a previously focused input
uninstall_extensiondestructiveUninstalls a Chrome extension by its ID.
uninstall_pwadestructiveUninstalls a Progressive Web App identified by its manifest ID and
upload_filewriteUpload a file through a provided element.
upload_toolwriteA tool with local-only file verification
wait_forreadWait for the specified text to appear on the selected page.
wrapped_enum_toolreadtest description

Details

Source
chromedevtools/chrome-devtools-mcp
npm
chrome-devtools-mcp@1.9.0
Transports
stdio
Credentials it reads
GEMINI_API_KEY
License
Apache-2.0
Stars
52,222 · pushed 0d ago

Trust audit

Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (8 observation(s))
Network
declared (4 observation(s))
Shell
declared (5 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (25)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
uninstall_extension, uninstall_pwa
Why it matters. 2 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWInventory / provenance · inv.binary · CWE-1104
tests/trace-processing/fixtures/basic-trace.json.gz
basic-trace.json.gz
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
LOWInventory / provenance · inv.hidden_file · CWE-1104
.gitmodules
.gitmodules
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.prettierignore
.prettierignore
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.hidden_file · CWE-1104
.release-please-manifest.json
.release-please-manifest.json
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools/input.test.ts:896
let isChecked = await page.$eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools/input.test.ts:915
isChecked = await page.$eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools/input.test.ts:954
let swChecked = await page.$eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools/input.test.ts:973
swChecked = await page.$eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
tests/tools/input.test.ts:1002
let r1Checked = await page.$eval(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/telemetry/watchdog/ClearcutSender.ts:9
import {logger} from '../../utils/logger.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/telemetry/watchdog/main.ts:12
import {logger, flushLogs, saveLogsToFile} from '../../utils/logger.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/third_party/devtools-formatter-worker.ts:8
import '../../third_party/devtools-frontend/front_end/entrypoints/formatter_worker/formatter_worker-entrypoint.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/third_party/devtools-heap-snapshot-worker.ts:8
import '../../third_party/devtools-frontend/front_end/entrypoints/heap_snapshot_worker/heap_snapshot_worker-entrypoint.js';
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/third_party/index.ts:99
export * as DevTools from '../../third_party/devtools-frontend/mcp/mcp.js';
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/advanced-usage.md:109
Add the `--browser-url` option to your MCP client configuration. The value of this option should be the URL of the running Chrome instance. `http://127.0.0.1:9222` is a common default.
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/advanced-usage.md:118
"--browser-url=http://127.0.0.1:9222"
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/client-configurations.md:30
"--browser-url=http://127.0.0.1:9222"
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/client-configurations.md:317
- **Connection URL:** `http://127.0.0.1:8080/mcp`
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
docs/configuration.md:43
Connect to a running, debuggable Chrome instance (e.g. `http://127.0.0.1:9222`). For more details see: https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/main/docs/advanced-usage.md#connecting
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@blackwell-systems/gcf, @eslint/js, @google/genai, @rollup/plugin-commonjs, @rollup/plugin-json, @rollup/plugin-node-resolve, @stylistic/eslint-plugin, @toon-format/toon
Why it matters. 26 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
src/third_party/lighthouse-devtools-mcp-bundle.js
src/third_party/lighthouse-devtools-mcp-bundle.js
Why it matters. 3572855 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
tests/fixtures/example.heapsnapshot
tests/fixtures/example.heapsnapshot
Why it matters. 2369369 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
tests/fixtures/heap-1.heapsnapshot
tests/fixtures/heap-1.heapsnapshot
Why it matters. 1214756 bytes not read
INFOInventory / provenance · inv.oversize · CWE-1104
tests/fixtures/heap-2.heapsnapshot
tests/fixtures/heap-2.heapsnapshot
Why it matters. 1216999 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-09-18 · audit v0.4.0 · source sha ffd7af791934 · full audit: observations/trust-audit/mcp-server/chromedevtools__chrome-devtools-1.json · Report an issue or request a re-scan

Audit history

DateSourceVerdictGradeScoreChange
2026-09-18ffd7af791934SAFEB84first audit

Alternatives

Other servers in the same categories, safer ones first.

Questions

What is the Chrome DevTools MCP server?

Chrome DevTools for coding agents

What tools does Chrome DevTools expose?

84 in total: 70 read-only, 12 that write, and 2 that can delete or overwrite (uninstall_extension, uninstall_pwa). Every one is listed on this page with its risk.

Is Chrome DevTools safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (84/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Chrome DevTools need?

It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Chrome DevTools run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as chrome-devtools-mcp at 1.9.0.

How current is this page?

The grade is for one exact copy of the source (ffd7af791934), read on 2026-09-18. The repository is watched and re-audited when it changes.

Provenance: OBSERVED · read 2026-09-18 · job trust-audit-2026-09-18