SVGator

Every project the server returns includes aneditor_url— a deep link that opens the project in the SVGator editor, so you can always continue by hand where the assistant left off.

- list_projects— List the authenticated user's SVGator projects (newest first), with aneditor_urldeep link per row and a total count for pagination.
- get_project— Get a single project summary: title, preview, folder, timestamps, canvas size, background colour, animation timeline, and saved export settings.
- create_project— Create a new SVGator project from a full project JSON, owned by the authenticated user.
- replace_project— Replace an existing project's entire JSON with a supplied full project (validation runs before any mutation).
- duplicate_project— Make a copy of an existing project, optionally into a different folder or under a new title.
- move_project— Move a project to a different folder and/or rename it.

- get_skeleton— Get a cheap, token-light structure map of a project (element tree with names and keyframe counts only, never values) — step 1 of the editing loop.
- read_part— Read the exact value or element at an id-anchored path — step 2 of the editing loop.
- edit_part— Apply one validated edit (update, insert, move, or delete) at a path and persist it — step 3 of the editing loop.
- describe_shape— Get the exact JSON shape of one building block (element or animator) before authoring, so field names are never guessed.

- list_assets— List the authenticated user's reusable assets (static or animated SVG items), newest first.
- get_asset— Get a single asset including its fulldata({document, definitions}) payload.
- create_asset— Create a new reusable asset from an asset document.
- update_asset— Replace an existing asset's entire document.

- list_folders— List the authenticated user's folders (the labels projects are filed under).
- get_folder— Get a single folder (id, title, timestamps) by its id.
- create_folder— Create a new folder to organize projects.
- update_folder— Rename an existing folder.

- export_project— Export a project to a deliverable format (SVG, Lottie, React Native, Flutter, video, or GIF), with optional per-export overrides.
- get_render— Poll the status of a raster (video/GIF) render started byexport_projectand get the signed download URL when done.
- get_profile— Get the authenticated customer profile: name, email, plan, and teams.

The server is a remote MCP server: your MCP client (Claude, or any client speaking Streamable HTTP) connects tohttps://mcp.svgator.com/mcpand signs you in through SVGator's regular OAuth login. Your SVGator credentials stayserver-side only— the AI model never sees your access token or secret key; it only receives the tool results (project lists, structure maps, exported files). Tool inputs are validated against published schemas, and invalid requests return descriptive errors the assistant can read and correct.

The MCP server turns SVGator into something you can drive with plain language. Instead of clicking through the editor, you describe what you want and your AI assistant does it: pulling up a project, changing a color, animating a logo, or exporting a finished file.

It's built for designers who want an assistant to handle the repetitive parts of animating, for marketing teams who need web-ready animations without waiting on a designer for every small change, and for developers who want production-ready exports (Lottie, React Native, Flutter, or SVG) that drop straight into a product. Every project comes back with a direct editor link, so you can always open it and finish by hand, saving tokens.

Here's what your assistant can do once it's connected:

- List projects: newest first, each with a direct editor link
- Search and page through large libraries
- Read project settings: canvas size, background, timeline, and export settings
- Create a project from a full definition
- Overwrite an existing project
- Duplicate a project: into the same or another folder
- Move or rename a project
- Organize projects into folders
- Manage reusable assets: list, read, create, and update

- Map a project's structure: element tree with keyframe counts, no heavy data
- See what's animated: which channels carry keyframes on each element
- Read exact values: any property, keyframe, or element
- Look up authoring shapes: the exact JSON for any element or concept

- Rectangles
- Circles and ellipses
- Lines, polylines, and polygons
- Custom paths
- Text and multi-line text
- Images
- Reused symbols and instances
- Groups
- Masks and clip paths

- Solid color fills: static or animated
- Gradient fills
- Strokes: solid or gradient, static or animated
- Compositing: blend modes and opacity
- Filter effects such as blur

- Add keyframes at specific times, with values
- Set static values where no motion is needed
- Read, inspect, and remove keyframes
- Set easing per keyframe: cubic bezier
- Animate transforms: position, rotation, scale, and skew
- Animate fill, stroke, compositing, and filter channels
- Morph one shape into another

- Export animated SVG: driven by JavaScript or CSS
- Set a start trigger: load, hover, click, scroll, or programmatic
- Set click and hover behavior: freeze, restart, reverse, or reset
- Export to Lottie
- Export to React Native or Flutter source
- Render video: MP4, MOV, AVI, MKV, or WebM
- Render GIF, WebP, PNG sequence, or ZIP
- Control looping: iterations, direction, ping-pong, and speed
- Set frame rate, resolution, and quality
- Handle transparency and background color

Start from your own artwork, then animate:Generating original shapes from scratch is the hardest thing to get right in any AI assistant. For the best results, build or bring in your SVG in SVGator’s editor first, then ask your assistant to animate it. That keeps your visual style consistent and lets the AI focus on what it does best: motion, timing, and sequencing.

Name your elements before you prompt:Your assistant reads element names to understand a project’s structure. Clear names like “left_arm”, “bg_circle”, or “headline” help it target the right element, avoid mistakes, and stay organized across complex scenes. Generic names make its job harder, and might end up costing you more tokens (depending on model .

Break complex animations into steps:Instead of “build me a full onboarding animation,” go one piece at a time: create the elements, add keyframes, then refine the timing. The server applies one validated change per edit, so smaller steps give you more control and make any mistake easy to catch and correct.

Be specific about timing and feel:“A smooth fade” is on the vague side. “A 400ms fade-in with ease-out” gives your assistant something concrete to work with. The more you describe the feel, whether snappy, bouncy, slow, or subtle, the closer the first result lands to what you had in mind.

Match the export format to where it will live:SVG is the right pick for the web, with your choice of JavaScript or CSS-only (for even better performance). Lottie, React Native, and Flutter hand off cleanly to app and mobile projects. Video and GIF are ready for social and email, where an animated SVG will not play. Choosing the format up front saves a round of re-exporting.

Duplicate a project before big experiments:If you want the AI to rebuild something from the ground up, ask it to duplicate the project first, then make the changes on the copy. The original stays exactly as it was, so a bold experiment never costs you the working version.

Finish in the editor:Every project comes back with a direct editor link. Once the assistant gets you most of the way there, open the project and handle the final polish by hand. The AI does the heavy lifting, and you keep control of the details. It also saves tokens, since small tweaks by hand are quicker and cheaper than having the assistant make each one.

Hosted MCP server for generating SVG illustrations, icons, and brand mascots with svgapp.ai from MCP-compatible AI clients.

The Lottie Creator MCP brings your AI assistant directly into your animation workflow — giving it full access to LottieFiles Creator so it can build and edit Lottie animations on your behalf through natural language.

AI Video, Image & Audio Generation with over 150 models

You're agent can Chain 60+ AI image and video models on one workflow canvas

Hosted remote MCP server for AI image and video generation from one Streamable HTTP endpoint.

Generate and edit on-brand images, video, audio, and 3D from any MCP-compatible AI assistant.

design-context-bridge is an MCP server that turns any AI agent into a frontend developer who can actually read a Figma file — not guess from a screenshot. When you hand a developer a Figma and say "build this", they don't just copy the visible pixels. They open the file, identify the components, read the exact colors and type scale, infer the routes the app will need, figure out the hover and disabled states, and export the icons. This server gives the AI that same access, so it can do that work for you — faithfully, not approximately

Turns public data (World Bank, IMF, FRED, Eurostat, SEC filings) or your own CSV into an animated chart video, recomputing every figure from the source rows before export.

Remote MCP image conversion tool for PNG, JPEG, WebP, AVIF, GIF, SVG, and HEIC workflows.