rive-mcp
Enables creating, editing, inspecting, rendering, and live-previewing Rive (.riv) animations directly from Claude without needing the Rive editor or cloud subscription, including building .riv files from scratch and a local web studio for human-AI collaboration.
README
rive-mcp
Create, edit, inspect, render and live-preview Rive (.riv) animations from Claude — no Rive editor, no cloud, no subscription.
rive-mcp is a free MCP (Model Context Protocol) server that gives Claude (or any MCP client) full control over .riv files. Unlike the official Rive MCP (which requires the editor running) or paid third-party servers, it works with nothing but a .riv file — and it can even build .riv files from scratch by serializing the binary format directly.
Rendering runs the official Rive runtime (@rive-app/canvas-advanced WASM) inside headless Chromium, so what you see is exactly what ships.

<p align="center"><img src="docs/media/showcase.apng" width="420" alt="Animation generated entirely by riv_create"></p> <p align="center"><i>This animation was generated entirely by <code>riv_create</code> — no Rive editor involved.</i></p>
Highlights
- Generate
.rivfrom JSON — shapes, gradients, embedded PNGs, text, bones + skinning, IK, mesh deformation, keyframe animation with easing, multi-layer state machines, listeners, events, physics baking, particles - Losslessly edit existing
.riv— change any property, swap text, delete subtrees (references auto-remapped); round-trip verified pixel-perfect - Local web Studio — Rive-editor-style 3-pane UI (hierarchy / canvas with click-select & drag / inspector / timeline) with hot reload; edits apply live
- Human ⇄ AI loop — an "Instructions for AI" box in the Studio: you type feedback, the AI picks it up via
riv_studio_notesand fixes the file, your browser updates instantly - Auto-rig characters — one call turns a character PNG into a rigged
.rivwith cutout parts, bone-skinned head mesh, eye blink, idle/happy animations and a state machine - Everything verified — generated files are loaded, rendered and state-machine-driven by the official runtime in E2E tests
Tools (19)
| Tool | What it does |
|---|---|
riv_list |
Recursively find .riv files (size, format version) |
riv_inspect |
Full metadata: artboards, animations (duration/fps/loop), state machines and inputs |
riv_render_frame |
Render any moment to PNG (inline image + file) |
riv_render_gif |
Turn an animation into a preview GIF |
riv_render_apng |
Animated PNG export — 24-bit color + alpha transparency (plays on GitHub) |
riv_render_video |
Record an animation or state machine to WebM video |
riv_render_sprites |
Sprite-sheet PNG + JSON metadata (for game engines) |
riv_play_state_machine |
Set/fire inputs → advance → state-transition report (+ optional frame captures) |
riv_generate_code |
Integration code with real artboard/SM/input names (React / JS / Vue / Svelte / Flutter) |
riv_create |
Build a .riv from a JSON scene spec — validated with the official runtime, returns a preview |
riv_edit |
Lossless editing of existing .riv files: set properties, swap named text, delete subtrees, add/replace/remove keyframes |
riv_extract_assets |
Extract embedded images/fonts from a .riv |
riv_visual_diff |
Pixel diff of two .riv files with a highlighted diff image |
riv_dump |
Low-level binary structure dump (typeKeys / properties / hierarchy) |
riv_slice_image |
Cut character parts out of a PNG by polygon (for cutout rigging) |
riv_rig_character |
Character PNG → fully rigged .riv in one call |
riv_diff |
Structural diff between two .riv files |
riv_studio |
Local web Studio: Rive-editor-style dark UI — hierarchy tree, canvas select/drag/resize, inspector, keyframe timeline editing, undo/redo, playback speed, one-click export (PNG/APNG/GIF/WebM), live preview + hot reload, EN/JA |
riv_studio_notes |
Fetch instructions the human typed into the Studio UI |
Quick start
Install from npm:
npm install -g rive-mcp-server
# Register with Claude Code (user scope = available in every project)
claude mcp add --scope user rive -- rive-mcp
Or run from source:
git clone https://github.com/ODU33104/rive-mcp.git
cd rive-mcp
npm install
npm run build
claude mcp add --scope user rive -- node /absolute/path/to/rive-mcp/dist/index.js
A Chromium-based browser is auto-detected in this order (usually nothing to install):
RIVE_MCP_CHROMEenv var (path to Chrome/Edge executable)- Playwright browser cache
- Installed Chrome → Edge
Requires Node.js 20+.
The Studio: human ⇄ AI collaboration
riv_studio opens a local web page where a human can inspect, directly edit, and request changes to whatever the AI built (first-run guide included, UI in English/Japanese):
- Let the AI build — "create a bouncing-ball riv and open it with riv_studio"
- Touch it — click/drag objects on the canvas, tweak numbers & colors in the inspector (applies live)
- Ask the AI — type bigger changes into Instructions for AI, then say "check the studio notes" in chat
- When the AI edits the file, the browser hot-reloads instantly
Works without a scene JSON too: any .riv can be edited property-by-property through the hierarchy + inspector.
Character animation
Turn a single character PNG into a naturally moving .riv:
riv_slice_imagecuts out ears/tail/etc. by polygon,riv_rig_characterassembles the whole rig in one call: pivot groups, a seamless 2-bone head mesh for tilting, vector eyelid blink, idle/happy animations and ahappytrigger- Or compose manually with
riv_create: image embedding, grid meshes with per-vertex keyframes, bone chains with distance-weighted skinning, IK constraints
Example prompts
- "List the riv files in
samples/and inspect vehicles.riv" - "Render the
curvesanimation as a GIF" - "Create a riv of falling snow over a night sky and open it in the studio"
- "Rig
characters/cat.png— ears and tail should move, and it should look happy on click" - "Check the studio notes" (after typing feedback into the Studio UI)
- "Write the React integration code for this file"
Development
npm run build # vendor runtime assets + tsc
npm run test:e2e # spawns the real server, exercises all 18 tools over JSON-RPC (48 checks)
docs/riv-format.md documents the reverse-engineered knowledge of the .riv binary format used by the writer (typeKeys/propertyKeys resolved from the official rive-runtime type definitions vendored in vendor/rive-defs/defs.json).
Limitations
- Text-run enumeration is not exposed by the runtime API (access by name works)
- GIF output has no transparency (composited on a background color)
- The Canvas2D preview renderer can show mesh seams that don't exist in the file (WebGL/Skia render clean)
- Luau scripting and the Layout engine are not generated (runtime spec still moving)
License
Free to use (personal & commercial) — but not open source. This is source-available freeware:
- ✅ Use the software freely; the
.rivfiles and code it generates are yours without restriction - ❌ No modification, no redistribution, no derivative works
- ❌ No reverse engineering; no AI-assisted analysis, extraction or reproduction of the code (including use as training data)
See LICENSE for the exact terms. Bundled third-party components: Inter font (OFL 1.1), Rive runtime & type definitions (MIT, © Rive, Inc.).
rive-mcp is an unofficial tool and is not affiliated with or endorsed by Rive, Inc.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.