image-tiler-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHROME_PATH | No | Path to Chrome/Chromium binary | /usr/bin/chromium |
| CHROME_NO_SANDBOX | No | Disable Chrome sandbox (required in Docker without user namespaces) | 1 |
| TILER_ALLOWED_DIRS | No | Comma-separated list of allowed directories for file operations |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tilerA | Split images into optimally-sized tiles for LLM vision analysis, or capture web page screenshots and tile them. MANDATORY two-phase workflow — DO NOT skip Phase 1: Phase 1 (REQUIRED first): Provide ONLY the image source (filePath, sourceUrl, url, etc). DO NOT include preset, tileSize, or outputDir. Returns a model comparison table with token estimates and an outputDir. You MUST present this table to the user and ask which preset they prefer. DO NOT select a preset yourself — the user decides. If you must auto-select, always use the cheapest option. Phase 2: Call again with the user's chosen preset + the outputDir from Phase 1. Re-include your original image source (filePath, sourceUrl, etc.). For captures, use screenshotPath from Phase 1 instead of url. Returns tile summary with metadata and content hints (no tile images). Use tilesDir + start/end to fetch only the tiles you need. Stop after Phase 1 if you only need the screenshot (capture mode) or comparison data. 4 tiling presets available:
Supports: local files (filePath), remote images (sourceUrl), data URLs, base64, and web page capture (url — Chrome required). Tiles saved as WebP (default) or PNG. Auto-downscales images over 10000px by default. TOKEN COST NOTE: The get-tiles mode returns image tiles as inline base64, consuming significantly more tokens than typical text-only MCP tools. Each tile costs ~258-1590 tokens depending on preset. Use the Phase 2 summary and tile hints to fetch only non-blank, relevant tiles. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| tile-and-analyze | Tile a local image and analyze every tile at full resolution |
| capture-and-analyze | Capture a web page screenshot via Chrome, tile it, and analyze each tile |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| model-configs | Supported vision model presets with tile sizes and per-tile token estimates |
| usage-guide | Quick reference: workflow, presets, and tips for the image tiler |
TDQS
Scored across 1 tool
With only one tool, there is no risk of confusion between tools. The single tool is distinctly named and described.
The single tool name 'tiler' is clear and consistent with the server's purpose. Naming within the tool description follows a predictable pattern.
One tool for an image tiling server is on the low end, but the tool's complexity (two-phase workflow, multiple presets) justifies a single entry. It feels slightly thin but not inappropriate.
The tool covers the core domain of image tiling for LLMs, supporting various sources and presets. Minor gaps might include lack of tool-specific helper functions, but the workflow is complete.