Shapesoda
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Vectorize images: PNG/JPG to SVG, PDF, EPS, DXF. Turns logos, icons and scans into clean vectors.
| Author | com.shapesoda |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 1849 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Shapesoda": {
"url": "https://shapesoda.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (5)
create_uploadCreates a one-time upload link for a local image file (valid 10 minutes). Upload the file with the returned curl command, then pass upload_id to vectorize. Only for agents whose terminal can reach shapesoda.com (Claude Code, Cursor and similar); in Claude.ai and other chat apps the sandbox cannot upload there, so call open_editor instead.
Parameters:
filename— string — Optional file name, for reference only.
Hints: read-only no · destructive no · idempotent no · open-world no
vectorizeUse this when the user wants to convert a raster image (logo, icon, illustration, scan, screenshot; PNG, JPEG, WebP, BMP, GIF, TIFF) into a vector: SVG, PDF, EPS, DXF or a re-rendered PNG. Pass the image in exactly one way: image (a file attached to the chat message, ChatGPT), upload_id (from create_upload) or image_base64 (≤2 MB, only exact file bytes you already have as text). If none of these is available, for example an image attached in Claude.ai, call open_editor instead. Returns a download link per format, valid 24 hours (or retention_days), and the SVG inline when small. Uses 1 credit for all formats; mode=test is free and watermarked; mode=preview is a free PNG up to 1 MP whose link buys the vectors later (format=svg, 1 credit). Do not use for generating new images, editing photos or upscaling.
Parameters:
dpi— integer — Pixels per inch of PNG output; needs a size in pt, mm, cm or in. Default 300.draw— string — fill: filled shapes; stroke: outline of every shape; stroke_edges: only the borders between shapes, each once (no double cuts). Default from the preset.mode— string — test: free, watermarked result for building an integration. preview: free PNG up to 1 MP without watermark, no vectors; fetch its link with format=svg to buy the vectors for 1 credit. Neither is available for vectorize_url. Default live.unit— string — Unit for width/height: px (default), pt, mm, cm, in.image— object — Image file attached to the user's message in the chat (ChatGPT).scale— number — Output size as a multiple of the source size. Not with width/height.width— number — Physical output width in unit. With width only, the height follows the aspect ratio; with height too, a sheet of that size (see aspect). Up to 10 m.aspect— string — With both width and height: fit (default, whole drawing inside), fill (covers the sheet, excess cropped), stretch (exact size, distorted).colors— Number of colors: 'auto', 'unlimited', or an integer 2–32 (max_colors goes up to 256). Default auto.curves— string — all: curves and lines; lines: straight segments only; lines_arcs: DXF lines and arcs, other formats as lines.detail— string — Output detail for photos. Default auto.format— array — Output formats; several formats cost 1 credit together. Default: the preset's format (svg for web).height— number — Physical output height in unit (width follows the aspect ratio unless width is set too).layers— string — Shapes stacked on top of each other, cut out of each other, or cut out and grouped by color. Default from the preset.preset— string — Settings for the job: web (default), print (PDF, shapes cut out), cut (vinyl/stickers, 8 colors), laser (2-color outlines), embroidery (12 colors, no tiny shapes).align_x— number — Horizontal placement on the sheet, 0 left … 1 right (default 0.5). Needs width and height; not with aspect=stretch.align_y— number — Vertical placement on the sheet, 0 top … 1 bottom (default 0.5). Needs width and height; not with aspect=stretch.corners— string — Keep corners sharp or round them.denoise— integer — Noise reduction before tracing: 0 off … 3 strongest.palette— Fixed colors #rrggbb (2–256), as a list or a comma-separated string. Not combined with colors or max_colors.quality— string — Input quality: low for blurry/noisy/JPEG-heavy images. Default auto.group_by— string — Groups in the output: color (one per color) or layer (by nesting depth). SVG <g>, PDF layers, EPS blocks, DXF layers. Default: by color only for layers=cutouts_grouped (DXF always by color).min_area— integer — Smallest shape kept, in px²; smaller specks are dropped. Overrides the preset.upload_id— string — ID returned by create_upload after the file was uploaded.dxf_curves— string — DXF curves as lines (polylines, default), arcs or splines. curves=lines/lines_arcs wins.gap_filler— string — on: an underlay in the shape colors hides light gaps between shapes. Needs draw=fill. Default off.image_type— string — Kind of image: artwork with smooth (anti-aliased) edges, artwork with hard pixel edges, or photo. Default auto.max_colors— integer — Maximum number of colors (2–256). Not combined with colors or palette.max_pixels— integer — Downscale the input to at most this many pixels before tracing (faster, fewer nodes).smoothness— integer — Contour smoothing 1–10 (higher: smoother, fewer nodes).svg_version— string — SVG flavor: 1.1 (default), 1.0, or tiny1.2 (no opacity or gradient transforms).adobe_compat— boolean — true: SVG friendly to Adobe Illustrator (size always set, stroke widths in drawing coordinates).image_base64— string — Exact PNG/JPEG/WebP/BMP/GIF/TIFF file bytes in base64 (≤2 MB), only when you already have them as text (e.g. from reading the file in a terminal). Never transcribe an image you only see in the conversation; call open_editor instead. Use create_upload for larger files.stroke_color— string — Stroke color #rrggbb instead of the shape color; needs draw=stroke or stroke_edges.stroke_width— number — Stroke width; needs draw=stroke or stroke_edges. Output units, or source pixels with stroke_scaling=scale. Default: hairline.transparency— string — Transparent areas: keep (stay transparent), white, or a background color #rrggbb.png_antialias— string — Anti-aliasing in PNG output. Default on.retention_days— integer — Keep the result downloadable for this many days (default 24 hours). Live mode only.stroke_scaling— string — fixed (default): width stays in output units when resized; scale: width in source pixels scales with the drawing.svg_fixed_size— boolean — true (default): width/height on the root <svg>; false: only a viewBox (responsive).curve_tolerance— number — Curve fitting tolerance in source pixels (default ≈0.5): lower keeps more nodes. Also sets smoothness unless given.gap_filler_width— number — Gap filler width in source pixels (default 1). Needs gap_filler=on.palette_tolerance— number — With palette: how far (CIE76 ΔE) an image color may be from a palette color to snap to it; farther colors keep their own value.
Hints: read-only no · destructive no · idempotent no · open-world yes
open_editorread-onlyUse this when the user wants to vectorize an image but you cannot pass the image to vectorize (no image, upload_id or exact base64 bytes available), including when the user attached the image in Claude.ai: opens the Shapesoda window, where the user picks the file, sees the vector result and adjusts it. Does not vectorize by itself and uses no credits. Do not use for generating new images.
Hints: read-only yes · destructive no · idempotent yes · open-world no
revectorizeRe-vectorizes a stored result (result_id and token from vectorize) with other settings, free for 24 hours after the first vectorization. Used by the Shapesoda window.
Parameters:
result_id(required) — string — result_id from vectorize or revectorize.token(required) — string — Result token (the token parameter of the result links).colors— Number of colors: 'auto', 'unlimited', or an integer 2–32 (max_colors goes up to 256). Default auto.corners— string — Keep corners sharp or round them.palette— Fixed colors #rrggbb (2–256), as a list or a comma-separated string. Not combined with colors or max_colors.quality— string — Input quality: low for blurry/noisy/JPEG-heavy images. Default auto.min_area— integer — Smallest shape kept, in px²; smaller specks are dropped. Overrides the preset.image_type— string — Kind of image: artwork with smooth (anti-aliased) edges, artwork with hard pixel edges, or photo. Default auto.smoothness— integer — Contour smoothing 1–10 (higher: smoother, fewer nodes).transparency— string — Transparent areas: keep (stay transparent), white, or a background color #rrggbb.
Hints: read-only no · destructive no · idempotent no · open-world no
get_usageread-onlyShows how many credits were used this month and how many remain.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.