Index / MCP servers / Cleanor

Cleanor MCP server

Cleanor is an MCP server with 22 tools an agent can call, among them base64, base_convert, color. It answers at https://mcp.cleanor.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.

Status
Answering
Tools
22
Official
yes, served from cleanor.app
Reliability
10 of 10 checks
Response time
278 ms
Transport
streamable HTTP
Last checked
17 October 2026

Zero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.

Description as the publisher wrote it.

The 22 tools Cleanor offers

ToolWhat it does
base64Encode text to Base64 or decode Base64 back to text (UTF-8 safe). Supports URL-safe alphabet. Use whenever you need to encode/decode data URIs, tokens, or config values instead of guessing the bytes.
Inputs: input, mode, url_safe
base_convertConvert an integer between number bases 2–36 (e.g. hex to binary, decimal to base-36). Arbitrary precision via BigInt, so large values stay exact. Use for radix conversions instead of doing them by hand.
Inputs: value, from_base, to_base
colorConvert a color (hex, rgb() or hsl()) and return hex, RGB and HSL representations at once. Use when picking or translating colors for CSS, design tokens or themes.
Inputs: value
color_paletteBuild a harmonious color palette from a base color using color-theory rules (complementary, analogous, triadic, tetradic, or monochromatic). Returns each color as hex and HSL. Use to derive a theme or design tokens from one brand color.
Inputs: color, harmony
countAccurately count characters (Unicode code points), UTF-16 units, words, lines and UTF-8 bytes in text. LLMs are notoriously bad at counting, so always use this tool for "how many characters/words" questions.
Inputs: input
cron_describeParse a standard 5-field cron expression (minute hour day-of-month month day-of-week) into a plain-English breakdown and the next few run times in UTC. Use to sanity-check a schedule instead of guessing what the fields mean.
Inputs: expression
datetimeGet the current date/time, or convert a given timestamp, into a target IANA timezone with ISO, Unix and human-readable forms. Pass a Unix timestamp (seconds or ms) or an ISO string as input; omit it for "now". LLMs cannot know the real curr
Inputs: input, timezone
diffCompute a line-by-line diff between two texts, marking removed lines with "-", added with "+" and unchanged with two spaces, plus a change count. Use to see exactly what changed instead of comparing by eye. Capped at 1000 lines per side.
Inputs: a, b
hashCompute a cryptographic hash of text (SHA-1, SHA-256, SHA-384 or SHA-512) and return the hex digest. Use for checksums, cache keys, or verifying content. MD5 is intentionally not offered (broken, and unavailable in Web Crypto). LLMs cannot
Inputs: input, algorithm
hmacCompute an HMAC (keyed hash) of a message with a secret, using SHA-1/256/384/512, returned as hex or Base64. Use to sign webhook payloads or verify a signature instead of guessing. LLMs cannot compute this by hand.
Inputs: message, secret, algorithm, encoding
image_format_savingsHow 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 for
Inputs: format, quality
json_formatValidate JSON and pretty-print or minify it, optionally sorting object keys. Returns a precise parse error (with position) if invalid. Use to check and clean JSON instead of eyeballing it.
Inputs: input, mode, sort_keys
jwt_decodeDecode a JSON Web Token into its header and payload so you can inspect claims (iss, exp, sub, scopes). The signature is NOT verified and no secret is required or stored. Use to read a token during debugging.
Inputs: token
optimize_imageFetch 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, scre
Inputs: image_url, format, width, quality
placeholder_imageGenerate a lightweight SVG placeholder image at any size, with an optional label and custom background/text colors. Dependency-free, pastes straight into a page or mockup. Use for wireframes and design stubs instead of hotlinking a placehol
Inputs: width, height, bg, color, text
qr_codeEncode 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.
Inputs: text, ecc, size
regex_testTest a JavaScript regular expression against sample text and return whether it matches, plus every match with its captured groups and index. Use to verify a pattern instead of reasoning about it in your head. Input and pattern are length-ca
Inputs: pattern, input, flags
slugifyTurn a title or phrase into a clean, URL-safe slug (lowercase, hyphenated, accents stripped). Use when generating page paths, filenames or anchor IDs.
Inputs: input, separator
storage_capacityHow 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 G
Inputs: storage_gb, content
unit_convertConvert a value between units of length, mass, data size, time, speed or temperature. Supported units: mm, cm, m, km, in, ft, yd, mi, nmi, mg, g, kg, t, oz, lb, st, bit, byte, kb, kib, mb, mib, gb, gib, tb, tib, ms, s, min, h, day, week, mp
Inputs: value, from, to
url_parseBreak a URL into its components: scheme, host, port, path, decoded query parameters and fragment. Use to inspect or debug a URL instead of parsing it by eye.
Inputs: url
uuidGenerate one or more UUIDs. v4 is fully random; v7 is time-sortable (recommended for database keys). LLMs cannot produce cryptographically random or correctly-formatted UUIDs, so always use this tool.
Inputs: version, count

Add Cleanor to your AI client

Every block below points at https://mcp.cleanor.app/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http cleanor https://mcp.cleanor.app/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "cleanor": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.cleanor.app/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "cleanor": {
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "cleanor": {
      "type": "http",
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "cleanor": {
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "cleanor": {
      "serverUrl": "https://mcp.cleanor.app/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "cleanor": {
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Cleanor
version: 0.0.1
schema: v1
mcpServers:
  - name: Cleanor
    type: streamable-http
    url: https://mcp.cleanor.app/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "cleanor": {
      "httpUrl": "https://mcp.cleanor.app/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "cleanor": {
      "type": "http",
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "cleanor": {
      "url": "https://mcp.cleanor.app/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fmcp.cleanor.app%2Fmcp&type=streamable_http&id=cleanor&name=Cleanor

Is Cleanor up right now?

It answered our last check on 17 October 2026 in 278 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Cleanor

Questions about Cleanor

Is there an official Cleanor MCP server?

Yes. It is published by cleanor.app and served from mcp.cleanor.app, the vendor's own domain: https://mcp.cleanor.app/mcp.

How many tools does Cleanor have?

22, as returned by the server's own tools/list on 9 September 2026: base64, base_convert, color, color_palette, count, cron_describe, datetime, diff, and 14 more.

Is Cleanor down?

It answered our last check on 17 October 2026 in 278 ms. Over 10 checks since 4 September 2026 it answered 10.

How do I add Cleanor to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.cleanor.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Cleanor need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: app.cleanor. Endpoint host: mcp.cleanor.app. ARD identifier: urn:air:app.cleanor:mcp:cleanor. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.