Skip to content

VecSnap Image to SVG MCP server

com.vecsnap/image-to-svgvecsnap.comstreamable-httpv1.0.0Scanned

Convert images to clean SVG with few anchor points, plus centerline single lines.

8 tools: 1 can delete or cancel things, 3 change things and 4 only read.

Tools: 1 delete, 0 irreversible, 3 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 2
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 VecSnap Image to SVG MCP server can do

The VecSnap Image to SVG MCP server is published by vecsnap.com, a domain the MCP Registry verified. It has 8 tools. It can delete or cancel things (1 tool: unlock_file) and create or change data (3 tools: vectorize_image, create_upload and start_conversion). 4 tools only read.

1 tool reads private data (get_svg); 2 tools bring in text other people can write (vectorize_image and start_conversion); 2 tools can send data out of your system (vectorize_image and start_conversion). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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 11, 2026, version 1.0.0.

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.

8 tools

Deletes or cancels 1Claude Code: deny
  • unlock_fileOnly the VecSnap card calls this.No findings

    Why it is in this group

    • The name "unlock_file" says "unlock": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Only the VecSnap card calls this. The person pressed Download: it spends one credit from their VecSnap account, once per image, and answers the file's link.

    Annotations the server declares

    • title: Unlock the file
    • readOnlyHint: false
    • destructiveHint: true
    • openWorldHint: false
    • idempotentHint: true
Changes things 3Claude Code: ask
  • create_uploadOnly the VecSnap card calls this.No findings

    Why it is in this group

    • The name "create_upload" says "create": a word for a change.
    Description, as the server wrote it
    Only the VecSnap card calls this. It answers where to send the image the person dropped.

    Annotations the server declares

    • title: Create an upload
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • start_conversionOnly the VecSnap card calls this.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "start_conversion" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Only the VecSnap card calls this. It starts a conversion and answers at once, so the card can show it.

    Annotations the server declares

    • title: Start a conversion
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
  • vectorize_imageUse this when the user wants an image converted to SVG or vector (vectorize, trace, image to SVG): a logo, an icon, an illustration, a picture from an AI tool.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Use this when the user wants an image converted to SVG or vector (vectorize, trace, image to SVG): a logo, an icon, an illustration, a picture from an AI tool. It converts an image the user already has, and does not create new images. Pass the image as a file, or a public https link, and never a file name or made-up data. If you cannot pass it as either, call this with neither: a card in the chat lets them drop it, or the answer says where they can. It answers the conversion's figures and page_url, the person's VecSnap page. Converting is free; the file costs one credit, once per image, and the person saves it from the card or that page. Where a card shows, it holds the drawing, its figures and its cost. With no card, page_url is the person's way to the result.

    Annotations the server declares

    • title: Vectorize an image to SVG
    • readOnlyHint: false
    • destructiveHint: false
    • openWorldHint: true
    • idempotentHint: true
Only reads 4Show 4 read-only tools
  • get_conversionUse this when vectorize_image answered that a conversion is still running, to read how it stands and its figures.No findings

    Why it is in this group

    • The name "get_conversion" says "get": a word for reading.
    Description, as the server wrote it
    Use this when vectorize_image answered that a conversion is still running, to read how it stands and its figures.

    Annotations the server declares

    • title: Check a conversion
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • get_creditsUse this when the user asks how many VecSnap credits they have left.No findings

    Why it is in this group

    • The name "get_credits" says "get": a word for reading.
    Description, as the server wrote it
    Use this when the user asks how many VecSnap credits they have left.

    Annotations the server declares

    • title: Check credits
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • get_svgUse this when the user asks for the finished SVG file itself, to save or use it.Reads private dataNo findings

    Why it is in this group

    • The name "get_svg" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    Description, as the server wrote it
    Use this when the user asks for the finished SVG file itself, to save or use it. It never spends a credit. If the person has already unlocked this image, in the VecSnap card or on their VecSnap page, it answers download_url, a link that downloads the file for an hour (for the person or a program). If not, download_url is null and page_url is the person's way to unlock it, for one credit.

    Annotations the server declares

    • title: Get the SVG file
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • read_cardOnly the VecSnap card calls this.No findings

    Why it is in this group

    • The name "read_card" says "read": a word for reading.
    Description, as the server wrote it
    Only the VecSnap card calls this. It answers how a conversion stands, its picture and its figures.

    Annotations the server declares

    • title: Read a conversion for the card
    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true

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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__image-to-svg__get_svg"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 18, 2026, 16:21 UTC, unchanged since Nov 11, 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
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.vecsnap.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://vecsnap.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.vecsnap.com/mcp: tools/list returned 8 tools to an anonymous client, including unlock_file (destructive), vectorize_image (write), create_upload (write), start_conversion (write)

    What this check looks for

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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http image-to-svg https://mcp.vecsnap.com/mcp
claude mcp add --transport http image-to-svg https://mcp.vecsnap.com/mcp

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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__image-to-svg__get_conversion",
      "mcp__image-to-svg__get_svg",
      "mcp__image-to-svg__get_credits",
      "mcp__image-to-svg__read_card"
    ],
    "ask": [
      "mcp__image-to-svg__vectorize_image",
      "mcp__image-to-svg__create_upload",
      "mcp__image-to-svg__start_conversion"
    ],
    "deny": [
      "mcp__image-to-svg__unlock_file"
    ]
  }
}

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 image-to-svg. Review it before you use it.

Capability tags behind 3 rules
  • mcp__image-to-svg__vectorize_image untrusted-input, outbound
  • mcp__image-to-svg__get_svg private-data
  • mcp__image-to-svg__start_conversion untrusted-input, outbound

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/com.vecsnap/image-to-svg/verify?hash=6e626a14adae46b55f9ac7ed8567e6e7b4a966a87f4a3d1f301cc8d002b992f4" | jq -e '.changed == false'

Pinned hash 6e626a14adae, from Nov 11, 2026, 07:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.vecsnap/image-to-svg/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.vecsnap/image-to-svg
[![Anlyon Radar](https://radar.anlyon.com/badge/com.vecsnap/image-to-svg.svg)](https://radar.anlyon.com/servers/com.vecsnap/image-to-svg)

Source: MCP Registry. Synced Nov 11, 2026, 07:17 UTC.

VecSnap Image to SVG MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the VecSnap Image to SVG MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 4 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 VecSnap Image to SVG MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: unlock_file.

Can the VecSnap Image to SVG 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 VecSnap Image to SVG MCP server have?

8 tools: 1 destructive, 3 write, 4 read. unlock_file, vectorize_image, create_upload, start_conversion, get_conversion, get_svg, get_credits and read_card.

Does the VecSnap Image to SVG MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the VecSnap Image to SVG MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): vectorize_image and start_conversion.

Has the VecSnap Image to SVG MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.