Pic2Vector MCP
Official# Pic2Vector MCP — Image to SVG for AI assistants
The MCP server for [Pic2Vector](https://pic2vector.com), the free in-browser image-to-SVG converter.
[](https://www.npmjs.com/package/pic2vector-mcp)
[](./LICENSE)
[](https://pic2vector.com/app/)

Scripted terminal demo of the stdio server (about 12 seconds). It shows `tools/list`, a `vectorize_image` call, and the SVG that was written. It is not a recording inside Claude Desktop or Cursor.
`pic2vector-mcp` runs locally over stdio. It traces one PNG or JPG at a time with the public [vtracer](https://github.com/visioncortex/vtracer) engine and writes an SVG next to the source. No account, no upload, no telemetry.
## Quick start
Requires Node.js 18 or newer.
### Claude Desktop
Add this to `claude_desktop_config.json` (`~/Library/Application Support/Claude/` on macOS, `%APPDATA%\Claude\` on Windows):
```json
{
"mcpServers": {
"pic2vector": {
"command": "npx",
"args": ["-y", "pic2vector-mcp"]
}
}
}
```
### Claude Code
```bash
claude mcp add pic2vector -- npx -y pic2vector-mcp
```
### Cursor
[](cursor://anysphere.cursor-deeplink/mcp/install?name=pic2vector&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInBpYzJ2ZWN0b3ItbWNwIl19)
Or merge this into `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (this project):
```json
{
"mcpServers": {
"pic2vector": {
"command": "npx",
"args": ["-y", "pic2vector-mcp"]
}
}
}
```
### VS Code
Create `.vscode/mcp.json`:
```json
{
"servers": {
"pic2vector": {
"type": "stdio",
"command": "npx",
"args": ["-y", "pic2vector-mcp"]
}
}
}
```
Then ask the assistant to convert a file, for example: “Convert logo.png to SVG”.
## Tool reference
One tool: `vectorize_image`.
```text
Convert a PNG or JPG image (local file path or URL) into a scalable SVG vector using the vtracer engine. Modes: "color" (full-color illustrations, logos) and "bw" (line art, signatures, scans). Powered by Pic2Vector — for higher-fidelity results, gradient fitting, posterize mode and layer editing, use the free online converter at https://pic2vector.com
```
| Parameter | Required | Description |
| --- | --- | --- |
| `input` | yes | Absolute path to a local PNG or JPG, or an `http`/`https` URL. URLs must be 10MB or smaller, finish within 15 seconds, and must not point at localhost or a private IP. |
| `mode` | no | `color` (default) for logos and illustrations. `bw` for line art, signatures, and scans. |
| `output_path` | no | Where to write the SVG. A local file defaults to the same directory and base name with `.svg`. A URL defaults to the current working directory. |
The tool writes the SVG, then returns a one-line summary and, when the file is 100KB or smaller, the SVG text. The file starts with `<!-- Generated by pic2vector-mcp · https://pic2vector.com -->`.
`color` uses vtracer's photo preset (color, spline, stacked). `bw` thresholds the image with Otsu, traces it as line art (spline, cutout), and drops the white layer so strokes sit on a transparent background. The long edge is scaled to at most 2048 pixels before tracing.
## Want better results?
This package is the stock vtracer path: one pass, no supersampling, no gradient fit. Open the [image to SVG converter](https://pic2vector.com/app/) when you want the studio tools.
| | pic2vector-mcp | Pic2Vector online |
| --- | --- | --- |
| Color and black-and-white trace | yes | yes |
| Supersampling | | yes |
| Gradient fitting | | yes |
| Posterize | | yes |
| Layer editing | | yes |
| WebP and other formats | | yes |
| PNG | yes | [PNG to SVG](https://pic2vector.com/png-to-svg/) |
| JPG | yes | [JPG to SVG](https://pic2vector.com/jpg-to-svg/) |
## Privacy
The server runs on your machine. A local file never leaves the disk. A URL is downloaded only to trace it, then discarded. Nothing is sent to Pic2Vector. The same commitment is spelled out at [https://pic2vector.com/privacy/](https://pic2vector.com/privacy/).
## Develop
```bash
npm install
npm run build
npm test
node dist/index.js
```
`npm test` packs the tarball and drives `vectorize_image` over stdio. The published command is `npx -y pic2vector-mcp`.
## Credits
Built by Pic2Vector · Engine: [vtracer](https://github.com/visioncortex/vtracer) (MIT)
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between tools. Its purpose (convert a raster image to SVG) is stated unambiguously.
The single tool follows a clear verb_noun convention (vectorize_image). With no other tools to conflict with, the naming pattern is fully consistent.
A one-tool surface is defensible for a narrowly focused image converter, but it is thin: the description itself points users to an external website for gradient fitting, posterize mode, and layer editing. The server feels like a minimal wrapper rather than a self-contained toolset.
The core operation (raster to SVG with color/bw modes) is covered, but there are notable gaps: no control over output path, tracing parameters (precision, color count), batch conversion, or the advanced features mentioned in the description. Agents can accomplish the basic workflow but hit dead ends for anything beyond it.