SkillAgentSearch skills...

image-tiler-mcp-server

MCP server that prevents LLM vision downscaling, tiles large images & screenshots so Claude, GPT-4o, and Gemini see every detail

Install / Use

claude mcp add keiver -- npx -y github:keiver/image-tiler-mcp-server

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

78/100

Supported Platforms

Claude Code
Claude Desktop
Gemini CLI

Our assessment of image-tiler-mcp-server

image-tiler-mcp-server scores 78/100 on our quality scale, 795th of 948 AI & Machine Learning skills we index.

Its MCP Server is 22 KB long, well organised into 34 sections with 16 code examples: a thorough specification that gives an agent plenty to work with.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 9 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 86/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

image-tiler-mcp-server compared with similar skills

All 4 of these similar skills score higher than image-tiler-mcp-server; compare them before choosing.

SkillScoreStarsUpdatedFormat
image-tiler-mcp-server (this skill)by keiver7839mo agoMCP Server
claude-memby thedotmack100117.9ktodayCLAUDE.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
Agent-Reachby Panniantong100112.7k10d agoCLAUDE.md
Understand-Anythingby Egonex-AI10093.0k2d agoCLAUDE.md

Frequently asked questions

How do I install image-tiler-mcp-server?
Run claude mcp add keiver -- npx -y github:keiver/image-tiler-mcp-server. The install tabs above show the steps for each supported agent.
Which AI agents does image-tiler-mcp-server work with?
It is written for Claude Code, Claude Desktop and Gemini CLI, as a MCP Server file. Other agents that read the same format can often use it too.
Is image-tiler-mcp-server safe to use?
It is MIT-licensed and scores 86/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is image-tiler-mcp-server still maintained?
The repository was last updated about 9 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

image-tiler-mcp-server

npm version License: MIT Node.js >= 20

<a href="https://glama.ai/mcp/servers/@keiver/image-tiler-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@keiver/image-tiler-mcp-server/badge" /> </a>

MCP server that gives LLMs full-resolution vision by tiling large images and capturing full web pages before details are lost to automatic downscaling.

<figure align="center"> <img src="assets/preview.gif" alt="Preview of image tiling grid with advised vision models size and token estimates" width="100%" /> <figcaption><i>The server generates an interactive HTML preview for every image, showing per-model tile grids and token estimates</i></figcaption> </figure>

What You Can Do

  • Visual QA for web pages. Capture a URL, tile it, and let the LLM spot misaligned elements, wrong colors, and broken layouts at full resolution. Fix the code, re-capture, and verify the fix visually.

  • Mobile responsive testing. Capture at any viewport width with mobile emulation, retina scaling, and a real mobile user agent. The LLM reviews the full mobile layout tile by tile, catching responsive breakpoint issues that only appear on small screens.

  • Full-resolution image analysis. Diagrams, infographics, and design mockups lose critical details when LLMs downscale them. A 3,600 x 20,220px full-page capture that Claude would crush to ~279 x 1,568 becomes 76 analyzable tiles, each at native resolution.

  • Token-efficient tile inspection. Each tile gets entropy-based content classification: blank, low-detail, mixed, or high-detail. The LLM skips blank tiles entirely and focuses tokens on what matters.

  • Iterative visual workflow. Capture, analyze, fix, re-capture. Versioned output directories (_v1, _v2, ...) preserve each iteration so you can compare before and after without overwriting previous results.

Quick Start

Claude Code

claude mcp add image-tiler -- npx -y image-tiler-mcp-server

image-tiler is a local alias. You can name it anything you like. image-tiler-mcp-server is the npm package that gets downloaded and run.

See Claude Code MCP docs for more info.

<details> <summary>Codex CLI</summary>
codex mcp add image-tiler -- npx -y image-tiler-mcp-server

Or add to ~/.codex/config.toml:

[mcp_servers.image-tiler]
command = "npx"
args = ["-y", "image-tiler-mcp-server"]
</details> <details> <summary>VS Code (Cline / Continue)</summary>

Add to your VS Code MCP settings:

{
  "image-tiler": {
    "command": "npx",
    "args": ["-y", "image-tiler-mcp-server"]
  }
}
</details> <details> <summary>Cursor</summary>

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "image-tiler": {
      "command": "npx",
      "args": ["-y", "image-tiler-mcp-server"]
    }
  }
}
</details> <details> <summary>Claude Desktop</summary>

Add to your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "image-tiler": {
      "command": "npx",
      "args": ["-y", "image-tiler-mcp-server"]
    }
  }
}

Restart Claude Desktop after editing.

</details> <details> <summary>Global Install (faster startup)</summary>
npm install -g image-tiler-mcp-server

Then use the simpler config in any client:

{
  "command": "image-tiler-mcp-server"
}
</details> <details> <summary>From Source</summary>
git clone https://github.com/keiver/image-tiler-mcp-server.git
cd image-tiler-mcp-server
npm install
npm run build

Then point your MCP config to the built file:

{
  "command": "node",
  "args": ["/absolute/path/to/image-tiler-mcp-server/dist/index.js"]
}
</details> <details> <summary>Docker</summary>

Build the image:

git clone https://github.com/keiver/image-tiler-mcp-server.git
cd image-tiler-mcp-server
docker build -t image-tiler-mcp-server .

The image includes Chromium for URL capture. Chrome's --no-sandbox flag is enabled by default in the image because Docker containers don't provide the user namespaces that Chrome's sandbox requires. The container itself provides process isolation. To re-enable the sandbox (e.g. with --privileged or user-namespace support), pass -e CHROME_NO_SANDBOX=0.

{
  "command": "docker",
  "args": [
    "run", "--rm", "-i",
    "-v", "/path/to/your/images:/data",
    "-e", "TILER_ALLOWED_DIRS=/data",
    "image-tiler-mcp-server"
  ]
}

The -i flag is required (stdio transport). Mount a volume for any directories the server needs to read from or write to, and set TILER_ALLOWED_DIRS to restrict file access to those mounts.

To disable URL capture entirely (no Chrome, no network access):

{
  "command": "docker",
  "args": [
    "run", "--rm", "-i",
    "-e", "TILER_DISABLE_URL_CAPTURE=1",
    "-v", "/path/to/your/images:/data",
    "-e", "TILER_ALLOWED_DIRS=/data",
    "image-tiler-mcp-server"
  ]
}
</details>

Usage

Tile an image

tile ~/source.png and analyze content

The server reads image dimensions and generates an interactive HTML preview with per-model tabs showing grid overlays, tile counts, and token estimates. Pick the model that matches your use case, and the server tiles and returns batches for analysis.

Capture a web page

capture full page screenshot of https://tomotv.app

The server launches headless Chrome, scrolls through the page to trigger lazy-loaded images (loading="lazy"), then captures a full-page screenshot (scroll-stitching pages over 16,384px). Your assistant receives each section at full resolution and can identify layout issues, misaligned elements, or broken styling that downscaling would hide.

To get only the screenshot without tiling, just ask for a screenshot and stop after the comparison step.

Test a mobile layout

capture https://tomotv.app in mobile view

This is responsive QA, not just a different viewport. The server captures with mobile: true, which sets a 390px viewport, 2x retina scale, and a mobile Safari user agent. Sites that check for mobile UA or touch capability serve their mobile layout, so the LLM reviews exactly what a real phone user sees.

Customize tiling

| What | Example prompt | |------|---------------| | Target a specific model | "Tile hero.png for OpenAI" | | Keep full resolution | "Tile banner.png at full resolution, no downscaling" | | PNG output | "Tile diagram.png as lossless PNG" | | Tile from URL | "Download and tile https://keiver.dev/source.png" | | Tile from base64 | "Tile this base64 image: iVBORw0KGgo..." |

Presets

| Preset | Default tile | Tokens/tile | Max tile | ID | |--------|-------------|-------------|----------|-----| | Claude | 1092px | 1590 | 1568px | claude | | OpenAI (GPT-4o/o-series) | 768px | 765 | 2048px | openai | | Gemini | 768px | 258 | 768px | gemini | | Gemini 3 | 1536px | 1120 | 3072px | gemini3 |

OpenAI note: The openai config targets the GPT-4o / o-series vision pipeline (512px tile patches). GPT-4.1 uses a fundamentally different pipeline (32x32 pixel patches) and is not currently supported. It would require a separate model config with a different calculation approach.

Gemini 3 note: Gemini 3 uses a fixed token budget per image (1,120 tokens regardless of dimensions). Tiling increases total token cost but preserves fine detail. For cases where detail isn't critical, consider sending a single image instead.

Why Tile?

You screenshot a full page, paste it into Claude, and Claude crushes it to a thumbnail. Any image with a long edge over 1,568 pixels gets auto-downscaled to fit within ~1.15 megapixels. A 3,600 x 20,220px full-page capture becomes ~279 x 1,568, losing over 99% of its pixels before the model even sees it.

GPT-4o is more forgiving but still destructive: it scales your image to fit within 2,048px, then scales the shortest side down to 768px, then tiles internally. An 8,192px-wide NASA panorama becomes ~1,456 x 768 before GPT-4o's own tiling even begins.

Gemini 1.5/2.0 handles large images natively at 768px tiles without downscaling. Gemini 3, however, caps each image at a fixed token budget (1,120 tokens) regardless of size. Tiling gives each piece its own budget.

Each tile stays within the model's sweet spot, so the LLM processes it at full resolution.

What Happens Without Tiling

Using assets/portrait.png (3,600 x 20,220, a full-page National Geographic capture) as an example:

| Model | What happens | Impact | |-------|-------------|--------| | Claude | Auto-downscaled to ~279 x 1,568 | ~0.6% of original pixels survive | | GPT-4o | Downscaled to ~365 x 2,048, then internally tiled | ~1% of original pixels survive the downscale | | Gemini 3 | Capped at 1,120 tokens per image (default) | Fixed token budget regardless of image size |

Gemini 1.5/2.0 tiles large images natively at 768px without downscaling. For Gemini 3, tiling multiplies the total token budget by sending each tile as a separate image.

With Tiling

| Model | Tiles | Result | |-------|-------|--------| | Claude | 76 tiles at 1,092px | Every tile within 1,568px sweet spot, no downscaling | | GPT-4o | 135 tiles at 768px | Every tile under 2,048px, no pre-downscale needed | | Gemini 3 | 42 tiles at 1,536px | Each tile gets its own 1,120-token budget |

Using assets/landscape.png (8,192 x 4,320, NASA image gallery):

| Model | Without tiling | With tiling | |-------|----------------|-------------| | Claude | Auto-downscaled to ~1,568 x 827 (~3.7% of pixels survive) | 32 tiles at 1,092px, full analysis | | GPT-4o | Downscaled to ~1,456 x 768 (~3% of pixels survive) | 66 tiles at 768px, full resolution | | Gemini 3 | Capped at 1,120 tokens | 18 tiles at 1,536px, 18x token budget |

Based on published model vision documentation as of Feb 2026: Claude vision limits · OpenAI vision guide · Gemini image understanding · Gemini media resolution

How It Works

This MCP server:

  1. Reads the image dimensions and the target model's vision config
  2. Generates an interactive HTML preview with per-model tabs showing grid overlays, tile numbering, and token estimates
  3. Calculates an optimal grid that keeps every tile within the model's sweet spot
  4. Extracts tiles as individual images (WebP default, PNG optional) and saves them to disk
  5. Returns a metadata summary (grid layout, file paths, token cost, per-tile content hints)
  6. Serves tiles on demand: call with tilesDir + start/end to retrieve batches of up to 5 tiles

Web capture pipeline. For URLs, the server launches headless Chrome, triggers lazy-loaded images by scrolling the page, captures a full-page screenshot (scroll-stitching pages over 16,384px), then feeds the screenshot into the same tiling pipeline.

Auto-downscaling. Images over 10,000px on their longest side are automatically downscaled before tiling (configurable via maxDimension). This keeps tile counts reasonable and improves LLM comprehension by increasing content density per tile. Set maxDimension=0 to disable, or pass a custom value (e.g., maxDimension=5000) for more aggressive downscaling.

<details> <summary>Tool Reference</summary>

tiler

On

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars3
CategoryAI
Updated8mo ago
Forks1

Languages

TypeScript

Trust signals

86/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 low