chrome-devtools-cli

chrome-devtools-mcp CLI 可让你在终端中与浏览器交互。

设置

注意：如果这是你第一次使用 CLI，请参阅 references/installation.md 了解设置方法。安装是一次性的前置步骤，不属于常规 AI 工作流。

AI 工作流

1. 执行：直接运行工具。如果不知道目标页面的 ID，请运行 chrome-devtools list_pages 查找。后台服务会隐式启动；每次使用前不要运行 start/status/stop。
2. 检查：使用 chrome-devtools take_snapshot <pageId> 获取元素 <uid>。
3. 操作：使用 chrome-devtools click <pageId> <uid>、chrome-devtools fill <pageId> <uid> <value> 等。状态会在命令之间保持。

快照示例：

uid=1_0 RootWebArea "Example Domain" url="https://example.com/"
  uid=1_1 heading "Example Domain" level="1"

权限与文件访问

默认情况下，CLI 拥有完整的文件系统访问权限（--allowUnrestrictedPaths=true），因此文件保存参数（--filePath、--outputDirPath）和 upload_file 可以访问系统中的任意文件。传入 --allowUnrestrictedPaths=false 可将文件访问限制在 OS 临时目录中。

命令用法

chrome-devtools <tool> [arguments] [flags]

• 必需参数按位置传入；可选参数使用标志。
• 对任何命令使用 --help 查看用法详情。
• 输出默认为类似 Markdown 的纯文本；传入 --output-format=json 可输出 JSON。

输入自动化（来自快照的 ）

chrome-devtools take_snapshot 1 # Take a text snapshot of the page to get UIDs for elements
chrome-devtools click 1 "id" # Clicks on the provided element
chrome-devtools click 1 "id" --dblClick true --includeSnapshot true # Double clicks and returns a snapshot
chrome-devtools drag 1 "src" "dst" # Drag an element onto another element
chrome-devtools drag 1 "src" "dst" --includeSnapshot true # Drag an element and return a snapshot
chrome-devtools fill 1 "id" "text" # Type text into an input, textarea, or select an option
chrome-devtools fill 1 "id" "text" --includeSnapshot true # Fill an element and return a snapshot
chrome-devtools handle_dialog 1 accept # Handle a browser dialog (accept/dismiss)
chrome-devtools handle_dialog 1 dismiss --promptText "hi" # Dismiss a dialog with prompt text
chrome-devtools hover 1 "id" # Hover over the provided element
chrome-devtools hover 1 "id" --includeSnapshot true # Hover over an element and return a snapshot
chrome-devtools press_key 1 "Enter" # Press a key or key combination ("Control+A", "Escape")
chrome-devtools press_key 1 "Control+A" --includeSnapshot true # Press a key and return a snapshot
chrome-devtools type_text 1 "hello" # Type text using keyboard into a focused input
chrome-devtools type_text 1 "hello" --submitKey "Enter" # Type text and press a submit key
chrome-devtools upload_file 1 "id" "file.txt" # Upload a file through a provided element
chrome-devtools upload_file 1 "id" "file.txt" --includeSnapshot true # Upload a file and return a snapshot

导航

chrome-devtools close_page 1 # Closes the page by its index
chrome-devtools list_pages # Get a list of pages open in the browser
chrome-devtools navigate_page 1 --url "https://example.com" # Navigates the currently selected page to a URL
chrome-devtools navigate_page 1 --type "reload" --ignoreCache true # Reload page ignoring cache
chrome-devtools navigate_page 1 --url "https://example.com" --timeout 5000 # Navigate with a timeout
chrome-devtools navigate_page 1 --type "reload" --handleBeforeUnload "accept" # Handle before unload dialog
chrome-devtools navigate_page 1 --type "back" --initScript "foo()" # Navigate back and run an init script
chrome-devtools new_page "https://example.com" # Creates a new page
chrome-devtools new_page "https://example.com" --background true --timeout 5000 # Create new page in background
chrome-devtools new_page "https://example.com" --isolatedContext "ctx" # Create new page with isolated context
chrome-devtools select_page 1 # Select a page as a context for future tool calls
chrome-devtools select_page 1 --bringToFront true # Select a page and bring it to front

仿真

每次调用 emulate 都会替换之前配置的所有仿真设置（--extraHttpHeaders 除外），因此请在一次调用中传入所有所需设置。

chrome-devtools emulate 1 --networkConditions "Offline" # Emulate network conditions (resets other settings)
chrome-devtools emulate 1 --cpuThrottlingRate 4 --geolocation "0,0" # Emulate CPU throttling and geolocation (resets other settings)
chrome-devtools emulate 1 --colorScheme "dark" --viewport "1920x1080" # Emulate color scheme and viewport (resets other settings)
chrome-devtools emulate 1 --userAgent "Mozilla/5.0..." # Emulate user agent (resets other settings)
chrome-devtools resize_page 1 1920 1080 # Resizes the selected page's window

性能

chrome-devtools performance_analyze_insight 1 "NAVIGATION_0" "LCPBreakdown" # Get more details on a specific Performance Insight (pageId, insightSetId, insightName)
chrome-devtools performance_start_trace 1 --reload true --autoStop false # Starts a performance trace recording (reload, autoStop)
chrome-devtools performance_start_trace 1 --reload true --autoStop true --filePath "t.json.gz" # Start trace and save to a file
chrome-devtools performance_stop_trace 1 # Stops the active performance trace
chrome-devtools performance_stop_trace 1 --filePath "t.json.gz" # Stop trace and save to a file

内存

chrome-devtools take_heapsnapshot 1 "./snap.heapsnapshot" # Capture a memory heap snapshot

内存调试（需要 --memoryDebugging=true）

chrome-devtools get_heapsnapshot_summary "./snap.heapsnapshot" # Get snapshot summary stats
chrome-devtools compare_heapsnapshots "./base.heapsnapshot" "./target.heapsnapshot" # Compare two snapshots
chrome-devtools get_heapsnapshot_details "./snap.heapsnapshot" # Snapshot statistics and per-class aggregates (with class IDs)
chrome-devtools get_heapsnapshot_class_nodes "./snap.heapsnapshot" 18 # Inspect instances of a class (class ID from get_heapsnapshot_details)
chrome-devtools get_heapsnapshot_dominators "./snap.heapsnapshot" 123 # Dominator tree for node
chrome-devtools get_heapsnapshot_duplicate_strings "./snap.heapsnapshot" # Find duplicated strings
chrome-devtools get_heapsnapshot_edges "./snap.heapsnapshot" 123 # Node edges/references
chrome-devtools get_heapsnapshot_object_details "./snap.heapsnapshot" 123 # Object details by node ID
chrome-devtools get_heapsnapshot_retainers "./snap.heapsnapshot" 123 # Retaining objects
chrome-devtools get_heapsnapshot_retaining_paths "./snap.heapsnapshot" 123 # Shortest retaining paths
chrome-devtools close_heapsnapshot "./snap.heapsnapshot" # Free memory from loaded snapshot

网络

chrome-devtools get_network_request 1 # Get the currently selected network request for page 1
chrome-devtools get_network_request 1 --reqid 1 --requestFilePath "req.md" # Get request by id and save to file
chrome-devtools get_network_request 1 --reqid 1 --responseFilePath "res.md" # Save response body to file
chrome-devtools list_network_requests 1 # List all network requests for page 1
chrome-devtools list_network_requests 1 --pageSize 50 --pageIdx 0 # List network requests with pagination
chrome-devtools list_network_requests 1 --resourceTypes fetch # Filter requests by resource type
chrome-devtools list_network_requests 1 --includePreservedRequests true # Include preserved requests

调试与检查

chrome-devtools evaluate_script "() => document.title" --pageId 1 # Evaluate a JavaScript function on page 1
chrome-devtools evaluate_script "(a) => a.innerText" --pageId 1 --args 1_4 # Evaluate JS with UID arguments on page 1
chrome-devtools evaluate_script --pageId 1 --sourcePath /path/to/script.js --format script # Evaluate a local classic JavaScript file on page 1
chrome-devtools get_console_message 1 1 # Gets a console message by its ID
chrome-devtools get_css_styles 1 "1_4" # Get CSS styles with pagination on page 1 (default: 10 rules, pageIdx 0)
chrome-devtools get_css_styles 1 "1_4" --pageSize 20 --pageIdx 1 # Paginate CSS rules with custom page size and custom 0-based page index
chrome-devtools lighthouse_audit 1 --mode "navigation" # Run Lighthouse audit for navigation
chrome-devtools lighthouse_audit 1 --mode "snapshot" --device "mobile" # Run Lighthouse audit for a snapshot on mobile
chrome-devtools lighthouse_audit 1 --outputDirPath ./out # Run Lighthouse audit and save reports
chrome-devtools list_console_messages 1 # List all console messages
chrome-devtools list_console_messages 1 --pageSize 20 --pageIdx 1 # List console messages with pagination
chrome-devtools list_console_messages 1 --types error --types info # Filter console messages by type
chrome-devtools list_console_messages 1 --includePreservedMessages true # Include preserved messages
chrome-devtools take_screenshot 1 # Take a screenshot of the page viewport
chrome-devtools take_screenshot 1 --fullPage true --format "jpeg" --quality 80 # Take a full page screenshot as JPEG with quality
chrome-devtools take_screenshot 1 --uid "id" --filePath "s.png" # Take a screenshot of an element
chrome-devtools take_snapshot 1 # Take a text snapshot of the page from the a11y tree
chrome-devtools take_snapshot 1 --verbose true --filePath "s.txt" # Take a verbose snapshot and save to file
chrome-devtools screencast_start 1 --filePath "screen.mp4" # Starts an mp4 screencast recording on page 1
chrome-devtools screencast_stop 1 # Stops the active screencast on page 1

扩展程序

chrome-devtools list_extensions # Lists all the Chrome extensions installed in the browser
chrome-devtools install_extension "/path/to/extension" # Installs a Chrome extension from the given path
chrome-devtools uninstall_extension "extension_id" # Uninstalls a Chrome extension by its ID
chrome-devtools reload_extension "extension_id" # Reloads an unpacked Chrome extension by its ID
chrome-devtools trigger_extension_action "extension_id" # Triggers the default action of an extension by its ID

渐进式 Web 应用（需要 --categoryPwa=true）

chrome-devtools install_pwa "https://example.com/" "https://example.com/" # Install PWA by manifest ID and install URL
chrome-devtools launch_pwa "https://example.com/" # Launch installed PWA
chrome-devtools get_os_app_state "https://example.com/" # Get OS app installation state
chrome-devtools uninstall_pwa "https://example.com/" # Uninstall PWA and close windows

实验性功能

实验性工具默认处于禁用状态。在启动时使用相应的标志启用它们。

chrome-devtools click_at 1 100 200 # Clicks at the provided coordinates on page 1 (requires --experimentalVision=true)
chrome-devtools list_webmcp_tools 1 # List all WebMCP tools on page 1 (requires --categoryExperimentalWebmcp=true)
chrome-devtools execute_webmcp_tool 1 "tool_name" --input '{"arg":"val"}' # Execute a WebMCP tool on page 1 (requires --categoryExperimentalWebmcp=true)
chrome-devtools list_3p_developer_tools 1 # List third-party developer tools on page 1 (requires --categoryExperimentalThirdParty=true)
chrome-devtools execute_3p_developer_tool 1 "tool_name" --params '{"arg":"val"}' # Execute third-party developer tool on page 1 (requires --categoryExperimentalThirdParty=true)

服务管理

chrome-devtools start   # Start or restart chrome-devtools-mcp
chrome-devtools start --headless=false # Start with visible browser window
chrome-devtools status  # Checks if chrome-devtools-mcp is running
chrome-devtools stop    # Stop chrome-devtools-mcp if any