[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-marketplace-ChromeDevTools-chrome-devtools-mcp-zh-CN":3,"guides-for-ChromeDevTools-chrome-devtools-mcp":456,"similar-k1718stvkzt1rg0y1vknsm38zx86m2r6-zh-CN":457},{"_creationTime":4,"_id":5,"children":6,"community":52,"display":53,"evaluation":58,"identity":262,"isFallback":243,"parentExtension":264,"providers":265,"relations":273,"repo":274,"tags":454,"workflow":455},1778683762612.1228,"k1718stvkzt1rg0y1vknsm38zx86m2r6",[7],{"_creationTime":8,"_id":9,"community":10,"display":12,"identity":18,"providers":23,"relations":44,"tags":47,"workflow":48},1778684005442.3716,"k17e8weqk2g03y5nktaca7naf586ntgw",{"reviewCount":11},0,{"description":13,"installMethods":14,"name":16,"sourceUrl":17},"使用 Chrome DevTools 和 Puppeteer 在 Chrome 中进行可靠的自动化、深入调试和性能分析",{"claudeCode":15},"chrome-devtools-mcp","Chrome DevTools MCP","https://github.com/ChromeDevTools/chrome-devtools-mcp",{"basePath":19,"githubOwner":20,"githubRepo":15,"locale":21,"slug":15,"type":22},"","ChromeDevTools","zh-CN","plugin",{"evaluate":24,"extract":38},{"promptVersionExtension":25,"promptVersionScoring":26,"score":27,"tags":28,"targetMarket":36,"tier":37},"3.0.0","4.4.0",95,[29,30,31,32,33,34,35],"chrome","devtools","puppeteer","automation","debugging","performance","network","global","community",{"commitSha":39,"license":40,"plugin":41},"HEAD","Apache-2.0",{"mcpCount":11,"provider":42,"skillCount":43},"classify",6,{"parentExtensionId":5,"repoId":45,"translatedFrom":46},"kd7an8ppnz1q2np9tc5yw4qenn86mg6h","k17evynnzmmag96rw4rpybyydx86m0py",[32,29,33,30,35,34,31],{"evaluatedAt":49,"extractAt":50,"updatedAt":51},1778683836724,1778683762612,1778684005442,{"reviewCount":11},{"description":54,"installMethods":55,"name":57,"sourceUrl":17},"Bundled plugins for actuating and debugging the Chrome browser.",{"claudeCode":56},"ChromeDevTools/chrome-devtools-mcp","Chrome DevTools for Agents",{"_creationTime":59,"_id":60,"extensionId":5,"locale":61,"result":62,"trustSignals":241,"workflow":260},1778683809544.008,"kn7f3trvrp66fm1f9afnwwgn6986mmtq","en",{"checks":63,"evaluatedAt":211,"extensionSummary":212,"features":213,"nonGoals":219,"practices":223,"prerequisites":224,"promptVersionExtension":228,"promptVersionScoring":26,"purpose":229,"rationale":230,"score":27,"summary":231,"tags":232,"targetMarket":36,"tier":37,"useCases":235,"workflow":240},[64,69,72,75,79,82,86,90,93,96,100,104,107,111,114,117,120,123,126,129,133,137,141,145,150,153,156,159,163,166,169,172,175,178,181,185,189,193,197,201,205,208],{"category":65,"check":66,"severity":67,"summary":68},"Practical Utility","Problem relevance","pass","The description clearly states that the extension provides control and inspection of a live Chrome browser for AI coding assistants, addressing the problem of reliable automation, debugging, and performance analysis.",{"category":65,"check":70,"severity":67,"summary":71},"Unique selling proposition","The extension offers significant value over a simple prompt by providing programmatic access to Chrome DevTools, enabling deep inspection and automation that cannot be replicated by basic LLM capabilities alone.",{"category":65,"check":73,"severity":67,"summary":74},"Production readiness","The extension provides a comprehensive set of tools for browser control, debugging, and performance analysis, covering the full lifecycle of browser interaction for AI agents.",{"category":76,"check":77,"severity":67,"summary":78},"Scope","Single responsibility principle","The extension focuses on controlling and debugging the Chrome browser, a coherent domain, and does not quietly extend into unrelated areas like general-purpose testing or deployment.",{"category":76,"check":80,"severity":67,"summary":81},"Description quality","The displayed description accurately and concisely reflects the extension's purpose of bundling plugins for Chrome browser actuation and debugging.",{"category":83,"check":84,"severity":67,"summary":85},"Invocation","Scoped tools","The tools are generally scoped as narrow verb-noun specialists (e.g., `take_screenshot`, `navigate_page`), facilitating precise selection by the agent.",{"category":87,"check":88,"severity":67,"summary":89},"Documentation","Configuration & parameter reference","All configuration options and parameters are documented, including defaults, and precedence is clear through the JSON configuration examples.",{"category":76,"check":91,"severity":67,"summary":92},"Tool naming","Tool names are descriptive and follow a clear verb-noun pattern within the domain of browser control and debugging.",{"category":76,"check":94,"severity":67,"summary":95},"Minimal I/O surface","Tool inputs appear to request only necessary data, and outputs seem to return only promised payloads without excessive diagnostic information.",{"category":97,"check":98,"severity":67,"summary":99},"License","License usability","The project is licensed under Apache-2.0, which is a permissive open-source license, as indicated by the LICENSE file and trust signals.",{"category":101,"check":102,"severity":67,"summary":103},"Maintenance","Commit recency","The repository shows recent commits as of May 13, 2026, indicating active maintenance.",{"category":101,"check":105,"severity":67,"summary":106},"Dependency Management","The project uses npm and has a lockfile (`hasLockfile: true`), indicating good dependency management practices.",{"category":108,"check":109,"severity":67,"summary":110},"Security","Secret Management","No secrets are used by the extension itself, and it does not appear to handle or expose secrets from the browser instance to the MCP client in an unsafe manner, based on README disclaimers.",{"category":108,"check":112,"severity":67,"summary":113},"Injection","The extension's README implies a focus on controlling the browser and its DevTools, and there are no explicit indications of loading and executing untrusted third-party code as instructions.",{"category":108,"check":115,"severity":67,"summary":116},"Transitive Supply-Chain Grenades","The extension bundles its code and does not appear to fetch or execute external code at runtime, mitigating risks of transitive supply chain attacks.",{"category":108,"check":118,"severity":67,"summary":119},"Sandbox Isolation","The extension interacts with a browser instance, but the README does not indicate any actions that would modify files outside the browser's controlled scope or the extension's own data directory.",{"category":108,"check":121,"severity":67,"summary":122},"Sandbox escape primitives","There are no indications in the README or documentation that the extension employs detached processes or retry loops to bypass sandbox limitations.",{"category":108,"check":124,"severity":67,"summary":125},"Data Exfiltration","The README disclaims that the MCP client can inspect browser data, but the extension itself does not appear to have mechanisms for exfiltrating confidential data from the user's environment to a third party.",{"category":108,"check":127,"severity":67,"summary":128},"Hidden Text Tricks","The README content is clean and does not contain any hidden text tricks, invisible characters, or obfuscation techniques.",{"category":130,"check":131,"severity":67,"summary":132},"Hooks","Opaque code execution","The extension is distributed as source code and does not appear to use obfuscated scripts, base64 payloads, or runtime code fetching.",{"category":134,"check":135,"severity":67,"summary":136},"Portability","Structural Assumption","The extension interacts with a browser instance and its configuration specifies user data directories, but it does not seem to make assumptions about the user's project file layout.",{"category":138,"check":139,"severity":67,"summary":140},"Trust","Issues Attention","With 38 open and 105 closed issues in the last 90 days, the closure rate is approximately 73%, indicating good maintainer responsiveness.",{"category":142,"check":143,"severity":67,"summary":144},"Versioning","Release Management","The project has a `manifestVersion` of 0.26.0 and a `CHANGELOG.md`, indicating clear versioning and release management.",{"category":146,"check":147,"severity":148,"summary":149},"Code Execution","Validation","info","While the extension interacts with browser tools, the README does not explicitly mention the use of schema validation libraries for all inputs and outputs, though the nature of DevTools interactions may imply some level of structured data handling.",{"category":108,"check":151,"severity":67,"summary":152},"Unguarded Destructive Operations","The extension's primary function is browser control and debugging, which can be state-changing, but these operations are within the browser's context and not inherently destructive to the user's filesystem without explicit user action.",{"category":108,"check":154,"severity":67,"summary":155},"Error Handling","The README and linked documentation suggest that errors are handled and reported, with a troubleshooting guide available, implying a robust error handling mechanism.",{"category":146,"check":157,"severity":148,"summary":158},"Logging","The README mentions logging debug information to a file and usage statistics collection, but a dedicated audit log for destructive actions is not explicitly detailed.",{"category":160,"check":161,"severity":148,"summary":162},"Compliance","GDPR","The extension allows inspection of browser content, which may include personal data. While it doesn't submit this data to a third party by default, the disclaimers advise caution regarding sensitive information shared with MCP clients.",{"category":160,"check":164,"severity":67,"summary":165},"Target market","The extension's functionality is global and not tied to any specific geographic or legal jurisdiction.",{"category":134,"check":167,"severity":67,"summary":168},"Runtime stability","The extension is designed to interact with Chrome and Puppeteer, with clear requirements for Node.js and Chrome, suggesting good cross-platform compatibility within supported environments.",{"category":87,"check":170,"severity":67,"summary":171},"README","The README file is comprehensive, clearly states the extension's purpose, and provides detailed installation and usage instructions.",{"category":76,"check":173,"severity":67,"summary":174},"Tool surface size","The extension exposes a large number of tools (over 50), which is within the acceptable range for a comprehensive browser automation and debugging toolset.",{"category":83,"check":176,"severity":67,"summary":177},"Overlapping near-synonym tools","The tool names appear distinct and cover specific functionalities, avoiding near-synonyms that could cause ambiguity for the LLM.",{"category":87,"check":179,"severity":67,"summary":180},"Phantom features","All features mentioned in the README, such as performance insights and debugging capabilities, are supported by corresponding tools listed in the documentation.",{"category":182,"check":183,"severity":67,"summary":184},"Install","Installation instruction","The README provides clear, copy-pasteable installation and configuration instructions for various MCP clients, along with a basic usage prompt.",{"category":186,"check":187,"severity":67,"summary":188},"Errors","Actionable error messages","The README points to a troubleshooting guide and implies good error reporting through its structure, suggesting errors are actionable.",{"category":190,"check":191,"severity":67,"summary":192},"Execution","Pinned dependencies","The project utilizes npm and has a lockfile, indicating that its third-party dependencies are pinned.",{"category":76,"check":194,"severity":195,"summary":196},"Dry-run preview","not_applicable","The nature of browser automation and debugging tools does not lend itself to a traditional 'dry-run' preview of state-changing operations in the same way as infrastructure changes or data transformations.",{"category":198,"check":199,"severity":67,"summary":200},"Protocol","Idempotent retry & timeouts","While not explicitly stated as idempotent for all operations, the use of Puppeteer for automation implies mechanisms for waiting and handling browser states, and the presence of a troubleshooting guide suggests error handling including timeouts.",{"category":160,"check":202,"severity":203,"summary":204},"Telemetry opt-in","warning","Usage statistics collection is enabled by default and can be opted out via a flag or environment variable, which is not strictly opt-in.",{"category":76,"check":206,"severity":67,"summary":207},"Theme declaration","The marketplace description clearly defines the curation theme as 'Bundled plugins for actuating and debugging the Chrome browser.'",{"category":142,"check":209,"severity":67,"summary":210},"Per-entry version metadata","The `marketplace.json` indicates a version ('0.26.0') and sources from a specific repository, aligning with best practices for versioned entries.",1778683809429,"This extension provides a Model-Context-Protocol (MCP) server that allows AI coding assistants to control and inspect a live Chrome browser, leveraging Chrome DevTools for automation, debugging, and performance analysis.",[214,215,216,217,218],"Control and inspect live Chrome browser instances","Record performance traces and extract insights","Analyze network requests, take screenshots, and check console messages","Automate browser actions with Puppeteer","Support for various MCP clients and installation methods",[220,221,222],"Controlling browsers other than Chrome or Chromium-based ones","Acting as a general-purpose web scraping tool without browser context","Providing capabilities beyond browser automation and debugging",[],[225,226,227],"Node.js v20.19 or newer","Google Chrome current stable version or newer","npm","3.1.0","To empower AI coding assistants with advanced capabilities to automate, debug, and analyze the performance of web applications within a live Chrome browser environment.","The extension is highly polished with excellent documentation, recent commits, and robust features. The only minor finding is the default opt-in telemetry, which is clearly documented and easily disabled.","Comprehensive and well-maintained extension for controlling and debugging Chrome browsers.",[233,33,234,29,30,31],"browser-automation","performance-analysis",[236,237,238,239],"Debugging complex web application issues","Analyzing and optimizing web performance","Automating browser-based testing scenarios","Assisting AI agents in tasks requiring browser interaction",[],{"codeQuality":242,"collectedAt":244,"documentation":245,"maintenance":248,"popularity":255,"security":257,"testCoverage":259},{"hasLockfile":243},true,1778683788822,{"descriptionLength":246,"readmeSize":247},63,32903,{"closedIssues90d":249,"forks":250,"hasChangelog":243,"manifestVersion":251,"openIssues90d":252,"pushedAt":253,"stars":254},105,2504,"0.26.0",38,1778676021000,39452,{"npmDownloads":256},6163267,{"hasNpmPackage":243,"license":40,"smitheryVerified":258},false,{"hasCi":243,"hasTests":243},{"updatedAt":261},1778683809544,{"basePath":19,"githubOwner":20,"githubRepo":15,"locale":61,"slug":15,"type":263},"marketplace",null,{"evaluate":266,"extract":268},{"promptVersionExtension":228,"promptVersionScoring":26,"score":27,"tags":267,"targetMarket":36,"tier":37},[233,33,234,29,30,31],{"commitSha":39,"license":40,"marketplace":269,"plugin":272},{"name":270,"pluginCount":271,"version":251},"chrome-devtools-plugins",1,{"mcpCount":11,"provider":42,"skillCount":11},{"repoId":45},{"_creationTime":275,"_id":45,"identity":276,"providers":277,"workflow":449},1778683755605.5256,{"githubOwner":20,"githubRepo":15,"sourceUrl":17},{"classify":278,"discover":438,"extract":441,"github":442,"npm":448},{"commitSha":39,"extensions":279},[280,293,317,329,337,347,363,377,385],{"basePath":19,"description":54,"displayName":270,"installMethods":281,"rationale":282,"selectedPaths":283,"source":292,"sourceLanguage":61,"type":263},{"claudeCode":56},"marketplace.json at .claude-plugin/marketplace.json",[284,287,289],{"path":285,"priority":286},".claude-plugin/marketplace.json","mandatory",{"path":288,"priority":286},"README.md",{"path":290,"priority":291},"LICENSE","high","rule",{"basePath":19,"description":294,"displayName":15,"installMethods":295,"rationale":296,"selectedPaths":297,"source":292,"sourceLanguage":61,"type":22},"Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer",{"claudeCode":15},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at .github/plugin)",[298,300,301,302,305,307,309,311,313,315],{"path":299,"priority":286},".claude-plugin/plugin.json",{"path":288,"priority":286},{"path":290,"priority":291},{"path":303,"priority":304},"skills/a11y-debugging/SKILL.md","medium",{"path":306,"priority":304},"skills/chrome-devtools/SKILL.md",{"path":308,"priority":304},"skills/chrome-devtools-cli/SKILL.md",{"path":310,"priority":304},"skills/debug-optimize-lcp/SKILL.md",{"path":312,"priority":304},"skills/memory-leak-debugging/SKILL.md",{"path":314,"priority":304},"skills/troubleshooting/SKILL.md",{"path":316,"priority":286},".mcp.json",{"basePath":318,"description":319,"displayName":320,"installMethods":321,"rationale":322,"selectedPaths":323,"source":292,"sourceLanguage":61,"type":328},"skills/a11y-debugging","Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.","a11y-debugging",{"claudeCode":56},"SKILL.md frontmatter at skills/a11y-debugging/SKILL.md",[324,326],{"path":325,"priority":286},"SKILL.md",{"path":327,"priority":304},"references/a11y-snippets.md","skill",{"basePath":330,"description":331,"displayName":332,"installMethods":333,"rationale":334,"selectedPaths":335,"source":292,"sourceLanguage":61,"type":328},"skills/chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","chrome-devtools",{"claudeCode":56},"SKILL.md frontmatter at skills/chrome-devtools/SKILL.md",[336],{"path":325,"priority":286},{"basePath":338,"description":339,"displayName":340,"installMethods":341,"rationale":342,"selectedPaths":343,"source":292,"sourceLanguage":61,"type":328},"skills/chrome-devtools-cli","Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.","chrome-devtools-cli",{"claudeCode":56},"SKILL.md frontmatter at skills/chrome-devtools-cli/SKILL.md",[344,345],{"path":325,"priority":286},{"path":346,"priority":304},"references/installation.md",{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":292,"sourceLanguage":61,"type":328},"skills/debug-optimize-lcp","Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions \"largest contentful paint\", \"page load speed\", \"CWV\", or wants to improve how fast their hero image or main content renders.","debug-optimize-lcp",{"claudeCode":56},"SKILL.md frontmatter at skills/debug-optimize-lcp/SKILL.md",[354,355,357,359,361],{"path":325,"priority":286},{"path":356,"priority":304},"references/elements-and-size.md",{"path":358,"priority":304},"references/lcp-breakdown.md",{"path":360,"priority":304},"references/lcp-snippets.md",{"path":362,"priority":304},"references/optimization-strategies.md",{"basePath":364,"description":365,"displayName":366,"installMethods":367,"rationale":368,"selectedPaths":369,"source":292,"sourceLanguage":61,"type":328},"skills/memory-leak-debugging","Diagnoses and resolves memory leaks in JavaScript/Node.js applications. Use when a user reports high memory usage, OOM errors, or wants to analyze heapsnapshots or run memory leak detection tools like memlab.","memory-leak-debugging",{"claudeCode":56},"SKILL.md frontmatter at skills/memory-leak-debugging/SKILL.md",[370,371,373,375],{"path":325,"priority":286},{"path":372,"priority":304},"references/common-leaks.md",{"path":374,"priority":304},"references/compare_snapshots.js",{"path":376,"priority":304},"references/memlab.md",{"basePath":378,"description":379,"displayName":380,"installMethods":381,"rationale":382,"selectedPaths":383,"source":292,"sourceLanguage":61,"type":328},"skills/troubleshooting","Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.","troubleshooting",{"claudeCode":56},"SKILL.md frontmatter at skills/troubleshooting/SKILL.md",[384],{"path":325,"priority":286},{"basePath":19,"description":386,"displayName":15,"installMethods":387,"license":40,"rationale":388,"selectedPaths":389,"source":292,"sourceLanguage":61,"type":437},"MCP server for Chrome DevTools",{"npm":15},"server.json with namespace/server name at server.json",[390,392,394,395,396,399,401,403,405,407,409,411,413,415,417,419,421,423,425,427,429,431,433,435],{"path":391,"priority":286},"server.json",{"path":393,"priority":286},"package.json",{"path":288,"priority":286},{"path":290,"priority":291},{"path":397,"priority":398},"src/index.ts","low",{"path":400,"priority":398},"src/tools/ToolDefinition.ts",{"path":402,"priority":398},"src/tools/categories.ts",{"path":404,"priority":398},"src/tools/console.ts",{"path":406,"priority":398},"src/tools/emulation.ts",{"path":408,"priority":398},"src/tools/extensions.ts",{"path":410,"priority":398},"src/tools/input.ts",{"path":412,"priority":398},"src/tools/lighthouse.ts",{"path":414,"priority":398},"src/tools/memory.ts",{"path":416,"priority":398},"src/tools/network.ts",{"path":418,"priority":398},"src/tools/pages.ts",{"path":420,"priority":398},"src/tools/performance.ts",{"path":422,"priority":398},"src/tools/screencast.ts",{"path":424,"priority":398},"src/tools/screenshot.ts",{"path":426,"priority":398},"src/tools/script.ts",{"path":428,"priority":398},"src/tools/slim/tools.ts",{"path":430,"priority":398},"src/tools/snapshot.ts",{"path":432,"priority":398},"src/tools/thirdPartyDeveloper.ts",{"path":434,"priority":398},"src/tools/tools.ts",{"path":436,"priority":398},"src/tools/webmcp.ts","mcp",{"sources":439},[440],"manual",{"npmPackage":15},{"closedIssues90d":249,"description":443,"forks":250,"homepage":444,"license":40,"openIssues90d":252,"pushedAt":253,"readmeSize":247,"stars":254,"topics":445},"Chrome DevTools for coding agents","https://npmjs.org/package/chrome-devtools-mcp",[446,31,332,447,29,33,30,437],"mcp-server","browser",{"downloads":256},{"classifiedAt":450,"discoverAt":451,"extractAt":452,"githubAt":452,"npmAt":453,"updatedAt":450},1778683762439,1778683755605,1778683758506,1778683760729,[233,29,33,30,234,31],{"evaluatedAt":261,"extractAt":50,"updatedAt":261},[],[458],{"_creationTime":459,"_id":460,"community":461,"display":462,"identity":468,"providers":470,"relations":482,"tags":485,"workflow":486},1778698612243.148,"k173zz7pz5jrtxtr3d3vy4xn4n86n693",{"reviewCount":11},{"description":463,"installMethods":464,"name":466,"sourceUrl":467},"AI 代理的浏览器自动化",{"claudeCode":465},"vercel-labs/agent-browser","agent-browser","https://github.com/vercel-labs/agent-browser",{"basePath":19,"githubOwner":469,"githubRepo":466,"locale":21,"slug":466,"type":263},"vercel-labs",{"evaluate":471,"extract":479},{"promptVersionExtension":228,"promptVersionScoring":26,"score":472,"tags":473,"targetMarket":36,"tier":478},99,[233,474,475,476,477],"cli","webdriver","testing","ai-agent","verified",{"commitSha":39,"marketplace":480,"plugin":481},{"name":466,"pluginCount":271},{"mcpCount":11,"provider":42,"skillCount":11},{"repoId":483,"translatedFrom":484},"kd74a6sfc26xa0ec2tpntj8r2986mn0a","k171hvn0e2t3jzczxm3vzspj3186mgj7",[477,233,474,476,475],{"evaluatedAt":487,"extractAt":488,"updatedAt":489},1778698406247,1778698388091,1778698612243]