{"slug": "a-developer-toolkit-to-make-your-website-agent-ready", "title": "A developer toolkit to make your website agent-ready", "summary": "Google launched a new Lighthouse Agentic browsing category and enhanced Chrome DevTools to help developers make websites ready for AI agents. The tools provide deterministic audits for accessibility, stability, and WebMCP integration, enabling agents to reliably complete tasks like booking appointments or placing orders.", "body_md": "Published: June 22, 2026\n\nAs AI agents evolve from only generating text to browsing, interacting, and completing complex tasks on your website, developers need dedicated tools to ensure a high-quality experience for these non-human users. The new Lighthouse Agentic browsing category, coupled with enhancements to Chrome DevTools, provides deterministic audits and a testing framework to help you build agent-ready websites.\n\nThe shift to the agentic web involves two major stages: agents *searching* the\nweb and agents *using* the web.\n\nWhen agents are just searching for websites, the [principles for Search Engine\nOptimization (SEO) still\napply](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide).\nIn this blog post, we focus on the work that developers can do when an agent\ninteracts directly with the website.\n\n## Audit, improve, and debug your agent-ready website\n\nFor an AI agent to reliably complete a flow on your site, such as booking an appointment or placing an order, it needs predictable, machine-readable signals. Here are the tools to help you assess and improve that readiness.\n\n### Audit your website agentic-readiness\n\nThe new [Agentic browsing category](/docs/lighthouse/agentic-browsing/scoring)\nin Lighthouse is available starting from M150 and provides developers with a set\nof deterministic audits to assess how agent-friendly their websites are,\nencouraging the adoption of new industry standards.\n\n**What the audits check**: The audits focus on three key areas critical for machine interaction:** Accessibility**: Accessibility is for humans first. Agents rely on the[accessibility tree](https://web.dev/learn/accessibility/aria-html#the_accessibility_tree), derived from DOM for assistive technology (AT), as their primary data model. The Agentic Browsing audit verifies a subset of categories from the[Accessibility audit](/docs/lighthouse/accessibility/scoring)that are critical for machine interaction. For example, both audits verify that every interactive element has a programmatic name. A well-formed accessibility tree is the primary way AI agents understand your page.**Stability**: Measures visual stability using Cumulative Layout Shift (CLS) to ensure elements don't move unexpectedly, preventing agent misclicks.**WebMCP integration**: Checks for the availability of registered WebMCP tools, forms missing declarative WebMCP, and schema validity. Adopting WebMCP helps agents explicitly expose your site's logic and forms, making interaction reliable.\n\n**The score**: Unlike other Lighthouse categories, at the time of publication, Agentic Browsing is*informational and unbenchmarked*. The focus is on providing actionable signals (pass or fail status and warnings) rather than a definitive ranking.\n\nTo learn more about the specific audit checks and what you can do to improve,\nsee the documentation for [Agent browsing audits for\nLighthouse](/docs/lighthouse/agentic-browsing).\n\n### Make interactions between agent and website faster and more reliable\n\nWebMCP is a proposed standard that aims to expose structure tools to AI Agents\non existing websites, accelerating and simplifying agent interactions.\nFor more information about implementation, see [Read about\nWebMCP](/blog/webmcp-epp).\n\n### Implement latest features using your preferred coding agent\n\nModern Web Guidance provides a collection of best practices and skills to help\ndevelopers build agent-ready websites. It includes the `webmcp`\n\nskill, which\nlets you delegate implementation of the WebMCP tools to your coding agent.\nBy integrating Modern Web Guidance into your development workflow, you can\nensure your application is built with modern, agent-friendly standards from the\nground up. To learn more, see [Modern Web Guidance\ndocumentation](http://goo.gle/modern-web-guidance).\n\n### Test and debug your website with Chrome DevTools for agents\n\nFor deep debugging and iterative development, [Chrome DevTools for\nAgents](/docs/devtools/agents) offers a unique testing persona. It lets you\ntransform your own AI-assisted IDE or coding agent into a browsing agent, giving\nyou a high degree of control.\n\nWith DevTools for agents you can:\n\n**Simulate agent interaction:** You can simulate the precise steps an agent would take, effectively \"becoming the user\" (or the agent) to reproduce failures and verify that your website's flows are deterministic.**Direct Lighthouse invocation:** Your testing environment can directly invoke the`lighthouse_audit`\n\ntool on the active tab. This provides an instant, multi-category health check based on the page's current state, allowing you to verify fixes iteratively against the Agentic Browsing standards.**Screencast and debug:** The tool offers detailed logging and screencast capabilities, so you can see exactly how the agent perceives and interacts with the page. This exposes some machine-readable signals, such as the accessibility tree, that may confuse the agent.\n\nThis helps you ensure a high-quality experience for non-human users before deployment.\n\nTo learn more about capabilities and configuration of Chrome DevTools for\nAgents, see our [GitHub\nrepository](https://github.com/ChromeDevTools/chrome-devtools-mcp#chrome-devtools-for-agents).\n\nThe following example configuration of Chrome DevTools for Agents\n(`~/.gemini/config/mcp_config.json`\n\nfor AntigravityCLI or configured in\nAntigravity) connects to Chrome Canary.\n\n```\n{\n  \"mcpServers\": {\n    \"chrome-devtools\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"chrome-devtools-mcp@latest\",\n        \"--autoConnect\",\n        \"--categoryExperimentalWebmcp\",\n        \"--channel=canary\"\n      ]\n    }\n  }\n}\n```\n\nUse the example query:\n*\"Using Chrome DevTools MCP, go to\nhttps://googlechromelabs.github.io/webmcp-tools/demos/pizza-maker/ and create me\na pizza with 10 mushrooms and 2 bell peppers; make sure to give me a summary of\nwhat you did and what tools you called.\"*\n\nYou can also use DevTools for Agents to perform agentic-readiness Lighthouse audit:\n\n\"*I want to do an agentic lighthouse audit on\nhttps://googlechromelabs.github.io/webmcp-tools/demos/french-bistro/?notoolname\nusing Chrome DevTools MCP; give me a full summary.*\"\n\n## What's next\n\nTo contribute and join the discussion, see [the official Lighthouse\nrepository](https://github.com/GoogleChrome/lighthouse).\n\nFor more information about WebMCP, see [WebMCP\ndocumentation](/docs/ai/webmcp). For more information about Modern Web\nGuidance, see [Modern Web Guidance\ndocumentation](http://goo.gle/modern-web-guidance). For more information\nabout optimizing your website for generative AI, see [Optimizing your website\nfor generative AI features on Google\nSearch](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide).", "url": "https://wpnews.pro/news/a-developer-toolkit-to-make-your-website-agent-ready", "canonical_source": "https://developer.chrome.com/blog/agent-ready-toolkit?hl=en", "published_at": "2026-06-22 07:00:00+00:00", "updated_at": "2026-06-24 09:23:19.710380+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-infrastructure"], "entities": ["Google", "Lighthouse", "Chrome DevTools", "WebMCP"], "alternates": {"html": "https://wpnews.pro/news/a-developer-toolkit-to-make-your-website-agent-ready", "markdown": "https://wpnews.pro/news/a-developer-toolkit-to-make-your-website-agent-ready.md", "text": "https://wpnews.pro/news/a-developer-toolkit-to-make-your-website-agent-ready.txt", "jsonld": "https://wpnews.pro/news/a-developer-toolkit-to-make-your-website-agent-ready.jsonld"}}