An MCP server for AI agents

Stop reading plain markdown.
See it rendered.

Instead of answering with a wall of markdown text, your AI builds the real page — HTML, CSS, JS — and Htmly deploys it instantly. One tool call gives you a live link you can actually open and look at.

claude_desktop_config.json
{
  "mcpServers": {
    "htmly": {
      "url": "https://html.shloksheth.tech/sse"
    }
  }
}
Tool exposed: render_files
Works withClaude DesktopClaude CodeCursorVS CodeAny MCP client

In simple words

Normally your AI replies with a block of markdown you have to read and imagine. Htmly turns that answer into a real, rendered web page and deploys it in an instant — so you can see what it built, in a far more visual way, not just read about it.

Push-to-visualize

Your agent sends a bundle of HTML/CSS/JS through one tool — render_files — and gets back a live URL instantly.

Multi-file projects

Full project structures are supported: index.html, styles.css, app.js and more, written in parallel for speed.

Isolated workspaces

Every request gets its own cryptographically unique workspace, so previews never collide.

Zero install, remote-first

Built on Server-Sent Events. No package to download, no local process — just point your client at the URL.

How it works

Three steps from connecting the server to a live page.

01

Connect Htmly

Add the SSE endpoint to your AI client using any of the methods above. Takes about a minute.

02

Ask for a visual

Tell your agent what you want to see — "show me this data as a dashboard" — and it writes the HTML.

03

Open the live link

Htmly hosts the result and hands your agent a real URL. Click it and the page is already live.

Add Htmly your way

Same one-line endpoint, five different clients. Pick yours, copy the config, and you're connected.

Open Settings → Developer → Edit Config, then add Htmly to your mcpServers and restart the app.

claude_desktop_config.json
{
  "mcpServers": {
    "htmly": {
      "url": "https://html.shloksheth.tech/sse"
    }
  }
}

Frequently asked

MCP (Model Context Protocol) is an open standard that lets AI assistants use external tools. An MCP server exposes those tools — Htmly's tool is render_files, which turns code your AI writes into a hosted web page.

Give your AI a place to render.

Copy the endpoint, drop it into your client, and your next prompt can come back as a live web page.

https://html.shloksheth.tech/sse