Loading…
Zero-auth image optimization, storage/format research data, and dev utility tools (hashing, encoding, JWT, regex, and more).
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The cleanor MCP server exposes 22 tools, focused primarily on web capabilities. Its published description reads: "Zero-auth image optimization, storage/format research data, and dev utility tools (hashing, encoding, JWT, regex, and more)". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates cleanor F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check cleanor's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add cleanor to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.cleanor.app/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
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-generat
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, dash
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: optimize_image
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "image_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: hash
A tool description tries to alter the model’s use of another tool.
uessing.RecommendationDescriptions must describe only their own tool.
tool: hash
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
bly by hand, so always use this tool instead of guessing. {"type":"object","propertiRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: uuid
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
atted UUIDs, so always use this tool. {"type":"object","properties":{"version":{"typRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: base64
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url_safe"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: base64
A tool description tries to alter the model’s use of another tool.
ssing the bytes.RecommendationDescriptions must describe only their own tool.
tool: json_format
A tool description tries to alter the model’s use of another tool.
ng it.RecommendationDescriptions must describe only their own tool.
tool: count
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
at counting, so always use this tool for "how many characters/words" questions. {"tyRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: regex_test
A tool description tries to alter the model’s use of another tool.
about it in your head. Input and pattern are length-capped to keep it fastRecommendationDescriptions must describe only their own tool.
tool: cron_describe
A tool description tries to alter the model’s use of another tool.
the fields mean.RecommendationDescriptions must describe only their own tool.
tool: unit_convert
A tool description tries to alter the model’s use of another tool.
ating.RecommendationDescriptions must describe only their own tool.
tool: datetime
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: url_parse
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: url_parse
A tool description tries to alter the model’s use of another tool.
g it by eye.RecommendationDescriptions must describe only their own tool.
tool: base_convert
A tool description tries to alter the model’s use of another tool.
d.RecommendationDescriptions must describe only their own tool.
tool: diff
A tool description tries to alter the model’s use of another tool.
ing by eye. Capped at 1000 lines per side.RecommendationDescriptions must describe only their own tool.
tool: hmac
A tool description tries to alter the model’s use of another tool.
ng. LLMs cannot compute this by hand.RecommendationDescriptions must describe only their own tool.
tool: hmac
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "secret"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: placeholder_image
A tool description tries to alter the model’s use of another tool.
ervice.RecommendationDescriptions must describe only their own tool.
tool: color_palette
A tool description tries to alter the model’s use of another tool.
ld a harmonious color palette from a base color using color-theory ruRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
I builders. Use optimize_image to shrink/convert an image an AI generated or dRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: optimize_image
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
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/PN
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.
Compute 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
Generate 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.
Encode 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.
Validate 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.
Decode 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 deb
Convert 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.
Turn a title or phrase into a clean, URL-safe slug (lowercase, hyphenated, accents stripped). Use when generating page paths, filenames or anchor IDs.
Accurately 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" que
Test 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 yo
Parse 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 guessi
Convert 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, gi
Get 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 f
Break 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.
Convert 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 ha
Compute 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 b
Compute 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
Generate 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 desig
Build 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