Cleanor Tools
@cleanor-app
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.
Overview
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,
