A skill that turns a raster image, such as a PNG or JPEG, into a clean SVG vector file. SVG images are made from shapes and can scale without becoming blurry.

Use it to convert raster artwork into SVG format through svg.new.

It helps replace a pixel-based image with a scalable version suitable for resizing and editing.

vectorize — Skill for Claude Code by svgnew/mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add svgnew/mcp --skill vectorize

Clone the repo

git clone --depth 1 https://github.com/svgnew/mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/svgnew/mcp/vectorize/github.svg)](https://agentmods.dev/skills/svgnew/mcp/vectorize)

Your own site

<a href="https://agentmods.dev/skills/svgnew/mcp/vectorize"><img src="https://agentmods.dev/badge/skills/svgnew/mcp/vectorize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/svgnew/mcp/vectorize"><img src="https://agentmods.dev/badge/skills/svgnew/mcp/vectorize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 539 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.00539
Opus 5.5	$0.00022	$0.00216
Sonnet 5.5	$0.00011	$0.00108
Haiku 4.5	$0.00006	$0.00054

Measured yesterday against content hash 3c7c7f3737a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vectorize scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Larger local file (up to 20 MB):** call `create_upload`. It returns an `upload_id` and a `put_url`. Upload the file there with an HTTP PUT, for example `curl -sS -X PUT -H "Content-Type: image/png" --upload-file <pat

skills/vectorize/SKILL.md · 31 lines

What it actually says

Vectorize Image to SVG

Convert a raster image to a clean SVG with svg.new's tracing engine.

Before you start

Use the svg.new MCP tools from this plugin (named mcp__plugin_svg-vectorizer_svg-new__*, or mcp__svgnew__* if the user connected the server directly). They sign in with the user's svg.new account, so no API key is involved. If the tools are missing or say sign-in is needed, ask the user to run /mcp, pick the svg.new server and choose Authenticate.

Don't fall back to a local tracer (vtracer, potrace) unless the user asks for one.

Steps

Find the image from the user's request or $ARGUMENTS. svg.new takes PNG, JPEG and WebP.
Send it to the vectorize tool in one of three ways:
- Public HTTPS link: pass it as image_url (up to 20 MB).
- Small local file (up to about 100 KB): read it, base64-encode it and pass image as data:<mime>;base64,<data> (image/png, image/jpeg or image/webp).
- Larger local file (up to 20 MB): call create_upload. It returns an upload_id and a put_url. Upload the file there with an HTTP PUT, for example curl -sS -X PUT -H "Content-Type: image/png" --upload-file <path> "<put_url>", then call vectorize with the upload_id.
Save the result next to the input with an .svg extension. Write the SVG text if it came back inline; if it came back as a download link (valid for one hour), save it with curl -sL -o <name>.svg "<link>".
Report the output path, size, path count and the credits remaining.

Notes

Each vectorization costs 1 credit. Free accounts get 3 a day.
Pass output: "url" to always get a download link instead of inline SVG.
The result's ID opens in the editor at https://svg.new/edit/<id>.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday Changed · +20 lines · +40 tokens per session 3c7c7f3737a5
1mo ago First seen · 11 lines · 15 tokens per session scan A c3a02f6bd002

Subscribe to this mod's changes

vectorize is a skill published in the GitHub repository svgnew/mcp (1 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 539 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media Design and UX background-removal gemini-cli-extension image-to-svg mcp mcp-server model-context-protocol

design

Design and critique any visible UI, before and after building. Trigger on UI work: "improve the UI", "redesign", "polish", "make it look better", "visual upgrade", "design review", "design audit", "layout fix", "UX improvement", or any task whose deliverable is a page, screen, or component that renders. Shapes a…

getpapi/papi · 121 tokens

zenith

Author and modify editable .zen designs with the Zenith CLI. Use for posters, slides, diagrams, charts, brand kits, size variants, and CSV mail-merge. Export PNG, self-contained SVG with outlined text, or PDF with explicit raster fallback reports. Use other tools for photo generation, raster editing, and unrelated…

zenitheditor/zenith · 70 tokens

html-design-revision

Revise an existing HTML/CSS design file with small, safe edits. Use when asked to change a color, text, size, position or add an element to a design that already exists. Use other tools for building a design from scratch.

zenitheditor/zenith · 54 tokens

html-author

Build a finished one-page or multi-page design (flyer, letterhead, handout, deck, poster, menu, card, report, invoice) as a single HTML/CSS file at a fixed pixel size. Use when asked to design something from a brief, starting from nothing. Use other tools to edit an existing file.

zenitheditor/zenith · 70 tokens

conduct-witness

A procedure for independently observing an A2A or MCP agent and recording the observation in a public ledger. A2A and MCP are standards for agents to communicate with tools and other agents.

ogasurfproject-jpg/horizon-shield · 79 tokens

figma-edit

Use when reading or editing a Figma file through the figma-edit-mcp server — inspecting nodes; creating or modifying shapes, frames, text, styles, variables, components, instances, annotations, or prototype reactions; and recovering from the server's structured errors. Explains the plugin's hard constraints (scope…

neozhehan/figma-edit-mcp · 82 tokens

vectorize