MCP server · Browser automation

Image Tiler MCP server

Lets your AI see big images and full web pages at full resolution by cutting them into tiles.

This is a small helper that lets your AI look at large images and full web page screenshots without losing the fine details. It is handy for anyone who checks designs, reviews web layouts, or works with tall screenshots, diagrams, and infographics. You connect it once and then just ask your AI to tile or capture something.

What is an MCP server? The 30-second version

On its own, your AI can only chat and read text you paste in. An MCP server is a small helper program that gives your AI a new skill or a connection to another tool. This one gives your AI the skill of cutting big images and web page captures into smaller pieces so nothing gets squashed. When you ask, your AI uses this helper to slice the image and look at each piece clearly.

What this MCP server does

You ask your AI to tile an image or capture a web page. The helper reads the image size, works out the best grid for your chosen AI model, and cuts the picture into separate tiles. For web pages it opens the page in a hidden Chrome browser, scrolls to load lazy images, and takes a full page screenshot first. Then it hands the tiles back to your AI one batch at a time so it can look at each one at full size. You also get an HTML preview file showing the grid and rough token cost.

Flow diagram: you ask your AI “Tile hero.png for OpenAI”, the Image Tiler MCP server works in steps: reads the image size, then cuts it into tiles, then hands tiles to your AI, and you get back tiles and a preview file.

Click to zoom

What you can do with it

Tile a large image so your AI sees it at full resolution
Capture a full web page screenshot and tile it
Capture a page in mobile view for responsive checks
Compare tile counts and token estimates across AI models before tiling
Skip blank or low-detail tiles to save tokens
Save each run in its own versioned folder so you can compare before and after
Tile an image straight from a URL or pasted base64 text

Try asking your AI

“tile ~/source.png and analyze content”
“capture full page screenshot of https://tomotv.app”
“capture https://tomotv.app in mobile view”
“Tile hero.png for OpenAI”

What it gives back to you

You get a short summary in the chat: the grid layout, where the tile files were saved, the rough token cost, and a hint about what each tile contains. The tiles themselves come back in small batches of up to five images at a time. It also writes an interactive HTML preview file you can open to see the grid, tile numbers, and token estimates per model.

Before you start

What you need

Node.js 18 or newer (the free program that runs this helper)
Chrome or Chromium installed if you want to capture web pages
A folder on your computer where the tiles can be saved

Good to know

It can open web pages and read and write image files on your computer, so only point it at pages and folders you are happy for it to access.

Install it with your AI

Add Image Tiler MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Image Tiler MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.