About vectorise
Vectorize images to SVG and export to PDF, EPS, DXF, PNG, JPG, or WEBP via Vectorise.Me.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y vectorizer-mcpVECTORISE_API_KEYSecretAPI key from vectorise.me/app. Optional — anonymous works with basic limits.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| preset | enum | No | Friendly preset matching the app UI: auto (engine detects image type), logo (sharp edges, exact brand colours), illustration (drawings/cartoons/clipart), photo (smooth tonal gradients), pixel_art (pixel-faithful, exact colours), technical_drawing (line art, black & white). Explicit options you pass override preset values.auto | logo | illustration | photo | pixel_art | technical_drawing |
| color_mode | enum | No | Colour handling. Default colorcolor | grayscale | bw | outline |
| image_path | string | Yes | Absolute path to the input image file |
| output_path | string | No | Where to save the SVG. Defaults to the input path with a .svg extension |
| quality_tier | enum | No | Speed/quality trade-off. Default balanced_crisp (credits: fast=1, balanced_crisp=2, high_precision=5)fast | balanced_crisp | high_precision |
| palette_count | integer | No | Target number of colours (sets manual palette mode) |
| quality_profile | enum | No | Advanced: engine profile. Prefer `preset` unless you know the engine. Default autoauto | balanced_crisp | balanced_edge_clean | sharp_text_logo | sharp_guarded | photo_smooth | clipart | exact |
| preserve_exact_colors | boolean | No | Keep source colours without merging similar shades |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.