{
  "schemaVersion": "1.0",
  "item": {
    "slug": "playwright-mcp",
    "name": "Playwright MCP",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Spiceman161/playwright-mcp",
    "canonicalUrl": "https://clawhub.ai/Spiceman161/playwright-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/playwright-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=playwright-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "examples.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/playwright-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/playwright-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/playwright-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/playwright-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/playwright-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": "Playwright MCP Skill",
        "body": "Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically."
      },
      {
        "title": "Installation",
        "body": "npm install -g @playwright/mcp\n# Or\nnpx @playwright/mcp\n\nInstall browsers (first time):\n\nnpx playwright install chromium"
      },
      {
        "title": "Start MCP Server (STDIO mode)",
        "body": "npx @playwright/mcp"
      },
      {
        "title": "Start with Options",
        "body": "# Headless mode\nnpx @playwright/mcp --headless\n\n# Specific browser\nnpx @playwright/mcp --browser firefox\n\n# With viewport\nnpx @playwright/mcp --viewport-size 1280x720\n\n# Ignore HTTPS errors\nnpx @playwright/mcp --ignore-https-errors"
      },
      {
        "title": "1. Navigate and Extract Data",
        "body": "# MCP tools available:\n# - browser_navigate: Open URL\n# - browser_click: Click element\n# - browser_type: Type text\n# - browser_select_option: Select dropdown\n# - browser_get_text: Extract text content\n# - browser_evaluate: Run JavaScript\n# - browser_snapshot: Get page structure\n# - browser_close: Close browser"
      },
      {
        "title": "2. Form Interaction",
        "body": "1. browser_navigate to form URL\n2. browser_type into input fields\n3. browser_click to submit\n4. browser_get_text to verify result"
      },
      {
        "title": "3. Data Extraction",
        "body": "1. browser_navigate to page\n2. browser_evaluate to run extraction script\n3. Parse returned JSON data"
      },
      {
        "title": "MCP Tools Reference",
        "body": "ToolDescriptionbrowser_navigateNavigate to URLbrowser_clickClick element by selectorbrowser_typeType text into inputbrowser_select_optionSelect dropdown optionbrowser_get_textGet text contentbrowser_evaluateExecute JavaScriptbrowser_snapshotGet accessible page snapshotbrowser_closeClose browser contextbrowser_choose_fileUpload filebrowser_pressPress keyboard key"
      },
      {
        "title": "Configuration Options",
        "body": "# Security\n--allowed-hosts example.com,api.example.com\n--blocked-origins malicious.com\n--ignore-https-errors\n\n# Browser settings\n--browser chromium|firefox|webkit\n--headless\n--viewport-size 1920x1080\n--user-agent \"Custom Agent\"\n\n# Timeouts\n--timeout-action 10000      # Action timeout (ms)\n--timeout-navigation 30000  # Navigation timeout (ms)\n\n# Output\n--output-dir ./playwright-output\n--save-trace\n--save-video 1280x720"
      },
      {
        "title": "Login to Website",
        "body": "browser_navigate: { url: \"https://example.com/login\" }\nbrowser_type: { selector: \"#username\", text: \"user\" }\nbrowser_type: { selector: \"#password\", text: \"pass\" }\nbrowser_click: { selector: \"#submit\" }\nbrowser_get_text: { selector: \".welcome-message\" }"
      },
      {
        "title": "Extract Table Data",
        "body": "browser_navigate: { url: \"https://example.com/data\" }\nbrowser_evaluate: { \n  script: \"() => { return Array.from(document.querySelectorAll('table tr')).map(r => r.textContent); }\" \n}"
      },
      {
        "title": "Screenshot",
        "body": "browser_navigate: { url: \"https://example.com\" }\nbrowser_evaluate: { script: \"() => { document.body.style.zoom = 1; return true; }\" }\n# Screenshot saved via --output-dir or returned in response"
      },
      {
        "title": "Security Notes",
        "body": "By default restricts file system access to workspace root\nHost validation prevents navigation to untrusted domains\nSandboxing enabled by default (use --no-sandbox with caution)\nService workers blocked by default"
      },
      {
        "title": "Troubleshooting",
        "body": "# Update browsers\nnpx playwright install chromium\n\n# Debug mode\nnpx @playwright/mcp --headless=false --output-mode=stdout\n\n# Check installation\nplaywright-mcp --version"
      },
      {
        "title": "Links",
        "body": "Playwright Docs\nMCP Protocol\nNPM Package"
      }
    ],
    "body": "Playwright MCP Skill\n\nBrowser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.\n\nInstallation\nnpm install -g @playwright/mcp\n# Or\nnpx @playwright/mcp\n\n\nInstall browsers (first time):\n\nnpx playwright install chromium\n\nQuick Start\nStart MCP Server (STDIO mode)\nnpx @playwright/mcp\n\nStart with Options\n# Headless mode\nnpx @playwright/mcp --headless\n\n# Specific browser\nnpx @playwright/mcp --browser firefox\n\n# With viewport\nnpx @playwright/mcp --viewport-size 1280x720\n\n# Ignore HTTPS errors\nnpx @playwright/mcp --ignore-https-errors\n\nCommon Use Cases\n1. Navigate and Extract Data\n# MCP tools available:\n# - browser_navigate: Open URL\n# - browser_click: Click element\n# - browser_type: Type text\n# - browser_select_option: Select dropdown\n# - browser_get_text: Extract text content\n# - browser_evaluate: Run JavaScript\n# - browser_snapshot: Get page structure\n# - browser_close: Close browser\n\n2. Form Interaction\n1. browser_navigate to form URL\n2. browser_type into input fields\n3. browser_click to submit\n4. browser_get_text to verify result\n\n3. Data Extraction\n1. browser_navigate to page\n2. browser_evaluate to run extraction script\n3. Parse returned JSON data\n\nMCP Tools Reference\nTool\tDescription\nbrowser_navigate\tNavigate to URL\nbrowser_click\tClick element by selector\nbrowser_type\tType text into input\nbrowser_select_option\tSelect dropdown option\nbrowser_get_text\tGet text content\nbrowser_evaluate\tExecute JavaScript\nbrowser_snapshot\tGet accessible page snapshot\nbrowser_close\tClose browser context\nbrowser_choose_file\tUpload file\nbrowser_press\tPress keyboard key\nConfiguration Options\n# Security\n--allowed-hosts example.com,api.example.com\n--blocked-origins malicious.com\n--ignore-https-errors\n\n# Browser settings\n--browser chromium|firefox|webkit\n--headless\n--viewport-size 1920x1080\n--user-agent \"Custom Agent\"\n\n# Timeouts\n--timeout-action 10000      # Action timeout (ms)\n--timeout-navigation 30000  # Navigation timeout (ms)\n\n# Output\n--output-dir ./playwright-output\n--save-trace\n--save-video 1280x720\n\nExamples\nLogin to Website\nbrowser_navigate: { url: \"https://example.com/login\" }\nbrowser_type: { selector: \"#username\", text: \"user\" }\nbrowser_type: { selector: \"#password\", text: \"pass\" }\nbrowser_click: { selector: \"#submit\" }\nbrowser_get_text: { selector: \".welcome-message\" }\n\nExtract Table Data\nbrowser_navigate: { url: \"https://example.com/data\" }\nbrowser_evaluate: { \n  script: \"() => { return Array.from(document.querySelectorAll('table tr')).map(r => r.textContent); }\" \n}\n\nScreenshot\nbrowser_navigate: { url: \"https://example.com\" }\nbrowser_evaluate: { script: \"() => { document.body.style.zoom = 1; return true; }\" }\n# Screenshot saved via --output-dir or returned in response\n\nSecurity Notes\nBy default restricts file system access to workspace root\nHost validation prevents navigation to untrusted domains\nSandboxing enabled by default (use --no-sandbox with caution)\nService workers blocked by default\nTroubleshooting\n# Update browsers\nnpx playwright install chromium\n\n# Debug mode\nnpx @playwright/mcp --headless=false --output-mode=stdout\n\n# Check installation\nplaywright-mcp --version\n\nLinks\nPlaywright Docs\nMCP Protocol\nNPM Package"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Spiceman161/playwright-mcp",
    "publisherUrl": "https://clawhub.ai/Spiceman161/playwright-mcp",
    "owner": "Spiceman161",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/playwright-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/playwright-mcp",
    "agentUrl": "https://openagent3.xyz/skills/playwright-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/playwright-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/playwright-mcp/agent.md"
  }
}