CleanVector MCP server
ai.cleanvector/cleanvectorcleanvector.aistreamable-httpv1.0.1Scanned
Create professional SVG artwork, icons and vector logos from a prompt, or vectorize any image.
11 tools: 3 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the CleanVector MCP server can do
The CleanVector MCP server is published by cleanvector.ai, a domain the MCP Registry verified. It has 11 tools. It can create or change data (3 tools: generate_illustration, generate_logo and vectorize_image), but cannot delete data. 8 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
11 tools
Changes things 3Claude Code: ask
generate_illustrationGenerate professional, editable SVG artwork from a text prompt: illustrations, icons, stickers and mascot scenes.No findings
Why it is in this group
- The name "generate_illustration" says "generate": a word for a change.
Description, as the server wrote it Generate professional, editable SVG artwork from a text prompt: illustrations, icons, stickers and mascot scenes. The result is real vector paths with a transparent background, not an embedded bitmap. Returns a task that processes asynchronously, so call wait_for_task with the returned id to get the result. Pass mascot_id (from list_mascots) to keep a consistent character across scenes. Costs 4 credits.
generate_logoGenerate a professional vector logo as editable SVG, delivered as a brand kit: the original mark, black and white variants, transparent PNG exports and a color palette measured fro…No findings
Why it is in this group
- The name "generate_logo" says "generate": a word for a change.
Description, as the server wrote it Generate a professional vector logo as editable SVG, delivered as a brand kit: the original mark, black and white variants, transparent PNG exports and a color palette measured from the finished artwork. An optional reference can refine an existing identity or provide loose inspiration. Runs asynchronously, so call wait_for_task with the returned id, then download_logo_kit. Costs 8 credits.
vectorize_imageConvert a raster image (PNG/JPG/WebP, max 5 MB) into a clean, editable SVG.No findings
Why it is in this group
- The description's first verb is "convert": a word for a change.
Description, as the server wrote it Convert a raster image (PNG/JPG/WebP, max 5 MB) into a clean, editable SVG. Provide image_url or image_base64. no_background defaults to true and isolates the subject (4 credits). Set no_background false with mode 'direct' to trace as-is (1 credit); mode 'enhance' redraws with AI first (4 credits). Runs async, so poll with wait_for_task.
Only reads 8Show 8 read-only tools
download_logo_kitReturn a completed logo kit as an embedded ZIP resource.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return a completed logo kit as an embedded ZIP resource. Includes three SVGs, three PNGs and palette.json. MCP output is capped at 2048px; use zip_url from the task result for larger files.
download_pngReturn the finished artwork as a PNG image (free on all plans).No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the finished artwork as a PNG image (free on all plans). Use after a task succeeded. For larger exports up to 8192px, use the png_url from the task result with the same Bearer key.
download_svgReturn the finished artwork as SVG markup.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Return the finished artwork as SVG markup. Use after a task succeeded.
get_accountCurrent plan and credit balance.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Current plan and credit balance. Costs: vectorize 1, generate/enhance 4, logo 8 credits. PNG and SVG downloads are free on every plan.
get_taskFetch the current status of a task.No findings
Why it is in this group
- The name "get_task" says "get": a word for reading.
Description, as the server wrote it Fetch the current status of a task. Status is one of queued, processing, succeeded, failed. A succeeded task includes the result with download URLs.
list_mascotsList the user's ready-to-use mascots (consistent characters).No findings
Why it is in this group
- The name "list_mascots" says "list": a word for reading.
Description, as the server wrote it List the user's ready-to-use mascots (consistent characters). Pass a mascot id to generate_illustration to place that character in a new scene. Mascots are created in the CleanVector dashboard.
list_tasksList the user's most recent tasks, newest first.No findings
Why it is in this group
- The name "list_tasks" says "list": a word for reading.
Description, as the server wrote it List the user's most recent tasks, newest first.
wait_for_taskBlock until a task settles (succeeded/failed) or the timeout passes.No findings
Why it is in this group
- The name "wait_for_task" says "wait": a word for reading.
Description, as the server wrote it Block until a task settles (succeeded/failed) or the timeout passes. Preferred over polling get_task in a loop. Generation typically takes 10-60 seconds.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:25 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://cleanvector.ai/api/mcp: tools/list returned 11 tools to an anonymous client, including generate_illustration (write), generate_logo (write), vectorize_image (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http cleanvector https://cleanvector.ai/api/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http cleanvector https://cleanvector.ai/api/mcp --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__cleanvector__get_task",
"mcp__cleanvector__wait_for_task",
"mcp__cleanvector__list_tasks",
"mcp__cleanvector__list_mascots",
"mcp__cleanvector__download_png",
"mcp__cleanvector__download_svg",
"mcp__cleanvector__download_logo_kit",
"mcp__cleanvector__get_account"
],
"ask": [
"mcp__cleanvector__generate_illustration",
"mcp__cleanvector__generate_logo",
"mcp__cleanvector__vectorize_image"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as cleanvector. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.cleanvector/cleanvector/verify?hash=e8bd34965240e57c4046e27ac5de306859de6cb17a3e457dd037971deead4cc7" | jq -e '.changed == false'Pinned hash e8bd34965240, from Nov 10, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.cleanvector/cleanvector/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.cleanvector/cleanvector)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:41 UTC.
CleanVector MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CleanVector MCP server safe?
- No scan can promise that. What its definitions show: 11 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the CleanVector MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CleanVector MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the CleanVector MCP server have?
- 11 tools: 3 write, 8 read. generate_illustration, generate_logo, vectorize_image, get_task, wait_for_task, list_tasks, list_mascots, download_png and 3 more.
Does the CleanVector MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CleanVector MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the CleanVector MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.