{
  "schemaVersion": "1.0",
  "item": {
    "slug": "chrome-devtools-mcp",
    "name": "Chrome Devtools Mcp",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/aiwithabidi/chrome-devtools-mcp",
    "canonicalUrl": "https://clawhub.ai/aiwithabidi/chrome-devtools-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/chrome-devtools-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=chrome-devtools-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/setup_chrome_mcp.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/chrome-devtools-mcp"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/chrome-devtools-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "🌐 Chrome DevTools MCP",
        "body": "Google's official Chrome DevTools MCP server — gives AI agents full control of a live Chrome browser via Puppeteer and the Chrome DevTools Protocol."
      },
      {
        "title": "Features",
        "body": "Input automation — click, drag, fill forms, hover, press keys, upload files, handle dialogs\nNavigation — open/close/switch pages, wait for elements/network idle\nScreenshots & snapshots — capture page state visually and as DOM\nPerformance traces — record and analyze Chrome performance traces with insights\nNetwork inspection — list/inspect network requests and responses\nConsole debugging — read console messages with source-mapped stack traces\nDevice emulation — emulate mobile devices, resize viewport\nForm automation — fill multiple form fields at once"
      },
      {
        "title": "Requirements",
        "body": "Node.js v20.19+ (already available in OpenClaw)\nChrome/Chromium browser"
      },
      {
        "title": "Install & verify",
        "body": "npx -y chrome-devtools-mcp@latest --help"
      },
      {
        "title": "Start the MCP server",
        "body": "# Standard (launches Chrome automatically)\nnpx -y chrome-devtools-mcp@latest\n\n# Headless mode (for servers)\nnpx -y chrome-devtools-mcp@latest --headless\n\n# Connect to existing Chrome (must be started with --remote-debugging-port=9222)\nnpx -y chrome-devtools-mcp@latest --browser-url=http://127.0.0.1:9222\n\n# Disable telemetry\nnpx -y chrome-devtools-mcp@latest --no-usage-statistics --no-performance-crux"
      },
      {
        "title": "OpenClaw MCP Integration",
        "body": "Add to your openclaw.json under MCP servers:\n\n{\n  \"mcp\": {\n    \"servers\": {\n      \"chrome-devtools\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"chrome-devtools-mcp@latest\", \"--headless\", \"--no-usage-statistics\"]\n      }\n    }\n  }\n}\n\nOr use the setup script:\n\npython3 {baseDir}/scripts/setup_chrome_mcp.py setup\npython3 {baseDir}/scripts/setup_chrome_mcp.py status\npython3 {baseDir}/scripts/setup_chrome_mcp.py test"
      },
      {
        "title": "Input Automation (8 tools)",
        "body": "ToolDescriptionKey ParamsclickClick an elementuid (required), dblClickdragDrag element onto anotherfrom_uid, to_uidfillType text into input/textarea/selectuid, valuefill_formFill multiple form elements at onceelements[]handle_dialogAccept/dismiss browser dialogsaction (accept/dismiss)hoverHover over elementuidpress_keyPress keyboard keykeyupload_fileUpload file to inputuid, paths[]"
      },
      {
        "title": "Navigation (6 tools)",
        "body": "ToolDescriptionKey Paramsnavigate_pageGo to URLurlnew_pageOpen new taburlclose_pageClose current tab—list_pagesList all open tabs—select_pageSwitch to tabindexwait_forWait for element/networkevent, uid, timeout"
      },
      {
        "title": "Debugging (5 tools)",
        "body": "ToolDescriptiontake_screenshotCapture page as imagetake_snapshotGet DOM/accessibility snapshotevaluate_scriptRun JavaScript in pagelist_console_messagesGet console log entriesget_console_messageGet specific console message"
      },
      {
        "title": "Performance (3 tools)",
        "body": "ToolDescriptionperformance_start_traceBegin performance recordingperformance_stop_traceStop and get trace dataperformance_analyze_insightAI analysis of trace"
      },
      {
        "title": "Network (2 tools)",
        "body": "ToolDescriptionlist_network_requestsList all network requestsget_network_requestGet request/response details"
      },
      {
        "title": "Emulation (2 tools)",
        "body": "ToolDescriptionemulateEmulate device (mobile, tablet)resize_pageChange viewport size"
      },
      {
        "title": "Test a webpage",
        "body": "navigate_page → URL\ntake_snapshot → get element UIDs\nclick/fill → interact with elements\ntake_screenshot → capture result"
      },
      {
        "title": "Performance audit",
        "body": "navigate_page → URL\nperformance_start_trace\nInteract with page\nperformance_stop_trace\nperformance_analyze_insight"
      },
      {
        "title": "Form testing",
        "body": "navigate_page → form URL\ntake_snapshot → identify form fields\nfill_form → fill all fields at once\nclick → submit button\ntake_screenshot → verify result"
      },
      {
        "title": "Privacy Notes",
        "body": "Google collects usage statistics by default — disable with --no-usage-statistics\nPerformance tools may send trace URLs to Google CrUX API — disable with --no-performance-crux\nAvoid sharing sensitive data in browser sessions"
      }
    ],
    "body": "🌐 Chrome DevTools MCP\n\nGoogle's official Chrome DevTools MCP server — gives AI agents full control of a live Chrome browser via Puppeteer and the Chrome DevTools Protocol.\n\nFeatures\nInput automation — click, drag, fill forms, hover, press keys, upload files, handle dialogs\nNavigation — open/close/switch pages, wait for elements/network idle\nScreenshots & snapshots — capture page state visually and as DOM\nPerformance traces — record and analyze Chrome performance traces with insights\nNetwork inspection — list/inspect network requests and responses\nConsole debugging — read console messages with source-mapped stack traces\nDevice emulation — emulate mobile devices, resize viewport\nForm automation — fill multiple form fields at once\nRequirements\nNode.js v20.19+ (already available in OpenClaw)\nChrome/Chromium browser\nQuick Start\nInstall & verify\nnpx -y chrome-devtools-mcp@latest --help\n\nStart the MCP server\n# Standard (launches Chrome automatically)\nnpx -y chrome-devtools-mcp@latest\n\n# Headless mode (for servers)\nnpx -y chrome-devtools-mcp@latest --headless\n\n# Connect to existing Chrome (must be started with --remote-debugging-port=9222)\nnpx -y chrome-devtools-mcp@latest --browser-url=http://127.0.0.1:9222\n\n# Disable telemetry\nnpx -y chrome-devtools-mcp@latest --no-usage-statistics --no-performance-crux\n\nOpenClaw MCP Integration\n\nAdd to your openclaw.json under MCP servers:\n\n{\n  \"mcp\": {\n    \"servers\": {\n      \"chrome-devtools\": {\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"chrome-devtools-mcp@latest\", \"--headless\", \"--no-usage-statistics\"]\n      }\n    }\n  }\n}\n\n\nOr use the setup script:\n\npython3 {baseDir}/scripts/setup_chrome_mcp.py setup\npython3 {baseDir}/scripts/setup_chrome_mcp.py status\npython3 {baseDir}/scripts/setup_chrome_mcp.py test\n\nTool Reference\nInput Automation (8 tools)\nTool\tDescription\tKey Params\nclick\tClick an element\tuid (required), dblClick\ndrag\tDrag element onto another\tfrom_uid, to_uid\nfill\tType text into input/textarea/select\tuid, value\nfill_form\tFill multiple form elements at once\telements[]\nhandle_dialog\tAccept/dismiss browser dialogs\taction (accept/dismiss)\nhover\tHover over element\tuid\npress_key\tPress keyboard key\tkey\nupload_file\tUpload file to input\tuid, paths[]\nNavigation (6 tools)\nTool\tDescription\tKey Params\nnavigate_page\tGo to URL\turl\nnew_page\tOpen new tab\turl\nclose_page\tClose current tab\t—\nlist_pages\tList all open tabs\t—\nselect_page\tSwitch to tab\tindex\nwait_for\tWait for element/network\tevent, uid, timeout\nDebugging (5 tools)\nTool\tDescription\ntake_screenshot\tCapture page as image\ntake_snapshot\tGet DOM/accessibility snapshot\nevaluate_script\tRun JavaScript in page\nlist_console_messages\tGet console log entries\nget_console_message\tGet specific console message\nPerformance (3 tools)\nTool\tDescription\nperformance_start_trace\tBegin performance recording\nperformance_stop_trace\tStop and get trace data\nperformance_analyze_insight\tAI analysis of trace\nNetwork (2 tools)\nTool\tDescription\nlist_network_requests\tList all network requests\nget_network_request\tGet request/response details\nEmulation (2 tools)\nTool\tDescription\nemulate\tEmulate device (mobile, tablet)\nresize_page\tChange viewport size\nCommon Workflows\nTest a webpage\nnavigate_page → URL\ntake_snapshot → get element UIDs\nclick/fill → interact with elements\ntake_screenshot → capture result\nPerformance audit\nnavigate_page → URL\nperformance_start_trace\nInteract with page\nperformance_stop_trace\nperformance_analyze_insight\nForm testing\nnavigate_page → form URL\ntake_snapshot → identify form fields\nfill_form → fill all fields at once\nclick → submit button\ntake_screenshot → verify result\nPrivacy Notes\nGoogle collects usage statistics by default — disable with --no-usage-statistics\nPerformance tools may send trace URLs to Google CrUX API — disable with --no-performance-crux\nAvoid sharing sensitive data in browser sessions"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aiwithabidi/chrome-devtools-mcp",
    "publisherUrl": "https://clawhub.ai/aiwithabidi/chrome-devtools-mcp",
    "owner": "aiwithabidi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/chrome-devtools-mcp",
    "agentUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/chrome-devtools-mcp/agent.md"
  }
}