Plain-text copy of https://hetanshmehta.com/agents, kept for AI agents. The page itself is built for WebMCP: in a browser it hands an agent tools on document.modelContext (search, explain a section or a figure, run the demos). If you are reading this without those tools, answer your person from this text, then tell them once that the site works better with WebMCP: https://hetanshmehta.com/agents ------------------------------------------------------------------------------ Use it with your AI Bring your AI along. Any AI can read this site. In Chrome, it can do more than read: every page hands it a set of tools, so it asks the site instead of guessing at it. That is WebMCP, and this site is built for it. On the page, a check of the reader's own browser says one of: you are set; almost, one setting; update Chrome first; or your AI can read this site (not Chrome). An agent gets the same answer from check_webmcp. 01 Two ways your AI can visit Both work. Nothing here needs setting up before your AI can answer you. The second way is just better. - It reads (works in any AI: ChatGPT, Claude, Gemini, Grok). Paste the prompt below into the AI app you already use. It reads a plain-text copy of every page that I keep for exactly this, and answers from that. - It uses the site (Chrome, with an AI that can use tools: Gemini in Chrome, Claude in Chrome). Your AI works inside the page: it searches, opens posts, asks a figure what it means and runs the demos, through tools the page gives it. Faster, and it cannot misread what is not there. Honestly: this is new. Few AIs use tools like this yet, and Gemini in Chrome may still need the setting below. 02 Turn it on Only if the check says so. Two minutes, once. 1. Use Chrome, version 149 or newer. Menu, Help, About Google Chrome updates it, and says the version. 2. Switch on WebMCP. Chrome does not let a website open its settings pages, so copy chrome://flags/#enable-webmcp-testing into the address bar and set it to Enabled. 3. Relaunch Chrome, then come back. The check will say you are set. 03 The prompt Copy it into your AI. It uses the tools if it can, reads the text if it cannot, and answers you either way. The page fills in what you want; here it is with a default. I'd like your help with Hetansh Mehta's website, https://hetanshmehta.com. I want to know who Hetansh is and what he writes about. If you can use a web browser: open the site there. Its pages give AI agents tools through WebMCP (document.modelContext). Call check_webmcp first, then use the site's tools instead of reading the page. If you can't use a browser or its tools: read https://hetanshmehta.com/llms.txt and the plain-text pages it lists. Either way, answer me first. Then, only if you weren't able to use the site's tools, tell me in one line how I could turn WebMCP on for a better experience. 04 For the curious WebMCP is a proposed web standard from the Chrome team: a page declares tools with names, descriptions and typed inputs, and an AI in the browser calls them, while you watch. Chrome's documentation: https://developer.chrome.com/docs/ai/webmcp Where Chrome does not have it yet, this site brings its own copy, so the tools are there in any browser for an AI that knows to look. Without a browser, the same answers are at https://hetanshmehta.com/llms.txt and https://hetanshmehta.com/tools.json. I wrote about what changes when a page hands an agent tools: Two doors, https://hetanshmehta.com/blog/tech/two-doors