agentmods.dev

vision-squeezer

vision-squeezer is an MCP server for Claude Code from eralpozcan/vision-squeezer. Its token cost is not measured, scanned A, original, no licence file.

A local MCP service that reduces the amount of image data sent to vision-language models by adjusting images to their processing tile boundaries.

In plain words
What is it for?
It is for preparing images before sending them to models such as Claude, GPT, Gemini, Llama, or Qwen.
Why use it?
It is intended to reduce the image information a model needs to process, which can lower vision-model token use.

MCP server for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: listed in a Claude config.

Part of the vision-squeezer-mcp plugin — 3 skills, 1 MCP server shipped together

not rated 2repo 1mo ago A scan tokens not measured custom licence

Good fit It is for preparing images before sending them to models such as Claude, GPT, Gemini, Llama, or Qwen.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer
View source ↗ eralpozcan/vision-squeezer visionsqueezer.com
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/eralpozcan/vision-squeezer

Made for: Claude Code.

Or install vision-squeezer-mcp, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vision-squeezer

README.md
[![agentmods](https://agentmods.dev/badge/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer/github.svg)](https://agentmods.dev/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer)
Your own site
<a href="https://agentmods.dev/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer"><img src="https://agentmods.dev/badge/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for vision-squeezer

Your own site · 80×15
<a href="https://agentmods.dev/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer"><img src="https://agentmods.dev/badge/mcp/eralpozcan/vision-squeezer/vision-squeezer-mcp-vision-squeezer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

vision-squeezer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/vision-squeezer-mcp/.mcp.json · 9 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 9 lines scan A a83e55d68c1a

Subscribe to this mod's changes

vision-squeezer is an MCP server published in the GitHub repository eralpozcan/vision-squeezer (2 stars, last pushed 1mo ago), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AILLMclaudegeminigpt4oimage-optimizationmcp
Related

Other mcp servers, from other repositories

vox-mcp

Multi-model AI gateway for MCP clients — routes prompts to Gemini, OpenAI, Anthropic, xAI, DeepSeek, Moonshot, OpenRouter, and local models with conversation memory. Runs locally from the vox-mcp Python package. Needs 8 environment variables to run.

linxule/vox-mcp · not measured

braintrust-lite

Multi-model AI consultation MCP for Claude Code — runs Claude, Codex, and Gemini in parallel for Judge-style synthesis. Runs locally from the braintrust-lite npm package.

HongjieRen/braintrust-lite · not measured

gemini-mcp-server

MCP server "gemini-mcp-server" as configured in salviz/gemini-mcp-server. Runs locally from the @salviz/gemini-mcp-server npm package.

salviz/gemini-mcp-server · not measured

promptfoo

TypeScript Execute (tsx): Node.js enhanced with esbuild to run TypeScript & ESM files. Runs locally from the tsx npm package.

promptfoo/promptfoo · not measured

veritasgraph

The first zero-trust, air-gapped Enterprise GraphRAG server for the Model Context Protocol (MCP). Runs locally from the veritasgraph-mcp Python package. Needs 3 environment variables to run.

bibinprathap/VeritasGraph · not measured

mcp

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.

ianreboot/safeprompt · not measured