# Vision Squeezer

> Use this tool when you need to optimize image processing for large language models (LLMs) to reduce token consumption and billing costs. Vision Squeezer preprocesses images by cropping and resizing them to model-specific dimensions, supporting popular models like Claude, GPT-4o, and Gemini. It integrates seamlessly with various development environments, including Claude Desktop and JetBrains IDEs, via the MCP protocol.

Canonical page: https://skillsregistry.net/skills/eralpozcan-vision-squeezer  
JSON: https://api.skillsregistry.net/v1/skills/eralpozcan-vision-squeezer

## Description

Vision Squeezer is a Rust-based MCP server that preprocesses images for LLM vision models to minimize token consumption and billing costs. It crops padding and resizes images to tile-boundary-aligned dimensions tailored to each model's tiling algorithm, supporting Claude, GPT-4o, GPT-5, and Gemini. Integrates as a background service with Claude Desktop, Cursor, VS Code Copilot, and JetBrains IDEs via the MCP protocol.

## Trust

- **Trust score (0–1):** 0.36
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/eralpozcan-vision-squeezer)
- **Repository:** <https://github.com/eralpozcan/vision-squeezer>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "eralpozcan-vision-squeezer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/eralpozcan-vision-squeezer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/eralpozcan-vision-squeezer/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt