What is vision-squeezer-mcp?

A Claude Code add-on that provides image optimization, sandboxed command execution, and image savings statistics through an MCP server. It also includes related skills for diagnosing, improving, and measuring image handling.

Use it to optimize images, run commands in a sandbox, and check image-related savings and statistics.

It puts the image tools and their supporting workflows together, so you do not need to install each part separately.

vision-squeezer-mcp — Plugin for Claude Code by eralpozcan: A Claude Code add-on that provides image optimization, sandboxed…

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.

Claude Code

/plugin marketplace add eralpozcan/vision-squeezer

agentmods

npx agentmods add plugins/eralpozcan/vision-squeezer/vision-squeezer-mcp

Clone the repo

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

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/eralpozcan/vision-squeezer/vision-squeezer-mcp.svg)](https://agentmods.dev/plugins/eralpozcan/vision-squeezer/vision-squeezer-mcp)

Your own site

<a href="https://agentmods.dev/plugins/eralpozcan/vision-squeezer/vision-squeezer-mcp"><img src="https://agentmods.dev/badge/plugins/eralpozcan/vision-squeezer/vision-squeezer-mcp.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 3 skills, 1 MCP server cost 263 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

vision-squeezer-mcp 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 5d 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/.claude-plugin/plugin.json · 14 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

Contents

What it installs

The manifest is a name and a version. 3 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 263 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

5d ago First seen · 14 lines scan A 7eb839e0d9ce

Subscribe to this mod's changes

vision-squeezer-mcp is a plugin published in the GitHub repository eralpozcan/vision-squeezer (2 stars, last pushed 1mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Creative and media LLM claude gemini gpt4o image-optimization mcp

claude-council

Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, Kimi, any model OpenRouter routes to, plus codex, antigravity, grok and kimi CLIs when installed, and a local ollama model) to get diverse perspectives on coding problems.

hex/claude-council · not measured

us-stock-analysis

Comprehensive US stock evaluation with fundamental, technical, economic, valuation, financial report, and position-management analysis — 26 analysis frameworks.

yennanliu/InvestSkill · not measured

tldr

Verdict-first communication mode. Cuts output tokens while keeping full technical accuracy.

0p9b/TLDR · not measured

msu

Skills and an MCP server for building on MapleStory Universe game data. The bundled maple-lookup MCP server searches the MSU Open API for characters, mobs, maps, skills, items, and sprites; the skills cover how that data is structured, how to choose between candidates, and how to turn it into something that renders.…

NEXPACE-Limited/msu-skills · not measured

game-tools

Quality checks and fixes for a game that already runs, on any engine or platform. It covers the parts of a game that are not features: how the controls feel, whether the numbers are balanced, whether the same input always gives the same result, whether the UI fits every screen and input device, whether the sound plays.