Cleanor Tools

Name: Cleanor Tools
Author: cleanor-app

@cleanor-app

Cleanor Tools について

Zero-auth hosted MCP for AI builders — 22 tools: image optimize/convert (WebP/AVIF/JPEG), QR, cited Cleanor Labs storage & image-format data, plus 18 deterministic dev utilities (hash, HMAC, UUID, JWT, JSON, regex, cron, datetime, color, diff…) LLMs get wrong. No API key.

#image-optimization #qr-code #storage #image-formats #ai-tools

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

cleanor-app

投稿者

Cleanor Labs

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "cleanor": {
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}

ツール

Fetch an image from a public URL and re-encode it smaller (WebP/AVIF/JPEG), optionally resizing to a target width. Returns the optimized image plus before/after byte sizes. Use this when an AI-generated or dropped-in asset (hero image, screenshot, illustration) is too large to ship.

How many photos or minutes of video actually fit in a given storage size, corrected for real OS/filesystem overhead. Backed by Cleanor Labs measured per-item sizes. Use for realistic sample copy, dashboards, or "how many photos fit in 128 GB" answers.

How much smaller WebP, AVIF or JPEG XL are than JPEG at matched perceptual quality, from Cleanor Labs’ controlled benchmark. Also reports the "HEIC conversion tax" (converting an iPhone HEIC to JPG/PNG makes it bigger). Use to justify a format choice when building a site or app.

Encode text or a URL as a QR code and return a crisp, dependency-free SVG you can paste straight into a page, deck or doc.

概要

What is Cleanor Tools?

Cleanor Tools is a zero‑auth, hosted Model Context Protocol (MCP) server that optimizes images and returns cited research data from Cleanor Labs. It is designed for AI builders who need image re‑encoding and verified device‑storage or image‑format statistics without signing up or managing API keys.

How to use Cleanor Tools?

Connect any MCP client to the Streamable HTTP endpoint https://mcp.cleanor.app/mcp. Alternatively, run the server locally via npx using the @cleanor/mcp package. Example configurations for Claude Code, Cursor, and Claude Desktop are provided in the README.

Key features of Cleanor Tools

Zero‑auth, hosted, and free MCP server
Optimize images to WebP, AVIF, or JPEG (optional resize)
Return cited research on storage capacity and format savings
22 read‑only tools for image, data, and developer operations
Streamable HTTP transport, no API key required
All responses link sources on cleanor.app

Use cases of Cleanor Tools

An AI agent optimizes a user‑generated image before storing or sharing it
A storage planning tool uses cited data to estimate photo/video capacity per GB tier
A workflow compares real‑world file‑size savings of modern image formats
A developer utility decodes JWTs, formats JSON, or tests regex without extra libraries
A design tool generates QR codes, color palettes, or placeholder images instantly

FAQ from Cleanor Tools

Does Cleanor Tools require an API key or signup?

No. The server is zero‑auth and every response is free with no account needed.

What is the server endpoint?

https://mcp.cleanor.app/mcp via Streamable HTTP. Local usage is also supported with npx -y @cleanor/mcp.

How many tools are available and are any dangerous?

22 tools are currently available. All are read‑only and explicitly safe to expose to autonomous agents. The first four handle image optimization and cited research data; the remaining 18 are deterministic developer utilities.

Where does the research data come from?

Real, cited data from Cleanor Labs studies, covering device storage capacity, next‑generation image‑format savings (WebP, AVIF,

「開発者ツール」の他のコンテンツ

Stakpak Agent CLI

stakpak

Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀

1.6K

Golf

golf-mcp

Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents

834