FastSVG MCP Server
Provides tools for constructing and manipulating SVG scenes — creating typed scene graphs, building exact Bézier paths, applying atomic patches, generating perceptually-interpolated gradients, and animating with keyframes and spring/bézier easing — then rendering those SVG scenes to raster output.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FastSVG MCP ServerCreate a 512x512 scene with a blue circle and render it to PNG."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI models shouldn't guess coordinates. FastSVG computes them.
Geometry, color, motion and APNG — solved with math, exposed over MCP.
Install
git clone https://github.com/Syron01/fastsvg && cd fastsvg
npm install && npm testnpx tsx apps/cli/src/main.ts render scene.json --out out.png # scene → PNG
npx tsx apps/cli/src/main.ts compare a.png b.png # pixel diffRelated MCP server: svg-mcp
Use with your model
{ "mcpServers": { "fastsvg": { "command": "npx", "args": ["fastsvg-mcp"] } } }"Animate the box 20px right, ease-in-out, export a 10fps APNG."
Ten tools: create_scene · apply_patch · build_path · create_gradient · render_png · export_apng · compare_images · …
What's inside
scene-ir | typed scene model, atomic patches |
geometry | exact Bézier bounds, arc length, reverse |
color-engine | sRGB ↔ linear ↔ OKLab, WCAG contrast |
gradient-engine | perceptual stops, ΔE banding report |
motion-engine | keyframes, cubic-bezier, damped springs, loop-seam check |
raster | alpha blending, 2×2 anti-aliased fills |
apng-exporter | PNG/APNG codec written from scratch |
frame-pipeline | scene + timeline → deterministic APNG |
vision | pixel diff, changed-region bbox, silhouette IoU |
Limits
Boolean ops, gradient raster fills and delta-frame APNG aren't implemented yet. Everything shipped is tested — full spec · live demo.
This server cannot be deployed
Maintenance
Related MCP Connectors
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models and 10 tools: up to 4 images per call, SVG vectorization, editing and more. Remote MCP with OAuth, no API keys. Pay per image, no subscription.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for Flux AI image generation
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server that turns AI into an SVG artist. One rendering engine with a rich JSON schema, AI controls all design parameters. Renders animated SVGs with CSS @keyframes and SMIL animations. Supports 16+ element types, parametric curves, pattern groups, gradient/filter/clip/mask definitions, and PNG preview. No external dependencies, runs locally via npx.370 npm30MIT
- AlicenseNot gradedqualityAmaintenanceA FastMCP server providing structured SVG authoring tools for LLMs, enabling create, edit, and render SVG graphics through hierarchical primitives, gradients, paths, and reusable resources.81 PyPI8GPL 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server that renders AI-authored documents to images and returns typed diagnostics for self-correction. It also provides visual QA metrics, raster-to-vector reconstruction, and image-to-draft proposals.MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server for creative generation and video production, letting AI agents author declarative animations, render deterministic frames, and measure output quality with perception instruments for brand and accessibility conformance.Apache 2.0