stitch-mcp
Import AI-generated UI designs from Google Stitch into your development workflow via MCP. Use when: converting Stitch designs to code, integrating AI design tools with coding agents, building UI from AI-generated prototypes.
What this skill does
# Stitch MCP
## Overview
Stitch MCP is a CLI for moving AI-generated UI designs from Google's Stitch platform into your development workflow. Stitch creates HTML/CSS designs through AI — stitch-mcp fetches those designs, serves them locally, builds deployable sites from them, and exposes them to coding agents via the Model Context Protocol (MCP).
The workflow: Design in Stitch, preview locally, hand off to a coding agent, ship production code.
## Instructions
### Prerequisites
- Node.js 18+
- Google Cloud account with Stitch access
- `gcloud` CLI installed
### Setup
```bash
npx @_davideast/stitch-mcp init
```
This guided wizard handles Google Cloud authentication, Stitch API access, and MCP client configuration.
### Preview Designs Locally
```bash
npx @_davideast/stitch-mcp serve -p <project-id>
```
Serves all project screens on a local Vite dev server.
### Build a Deployable Site
```bash
npx @_davideast/stitch-mcp site -p <project-id>
```
Maps Stitch screens to routes and generates a deployable Astro project.
### MCP Integration
Add to your MCP client config to give coding agents access to Stitch tools:
```json
{
"mcpServers": {
"stitch": {
"command": "npx",
"args": ["@_davideast/stitch-mcp", "proxy"]
}
}
}
```
### MCP Tools for AI Agents
| Tool | Description |
|------|-------------|
| `build_site` | Build a site from a project by mapping screens to routes |
| `get_screen_code` | Retrieve a screen's HTML code content |
| `get_screen_image` | Retrieve a screen screenshot as base64 |
### CLI Commands
| Command | Description |
|---------|-------------|
| `init` | Set up auth, gcloud, and MCP client config |
| `doctor` | Verify configuration health |
| `serve -p <id>` | Preview project screens locally |
| `view` | Interactive resource browser |
| `site -p <id>` | Generate Astro project from screens |
| `tool [name]` | Invoke MCP tools from CLI |
| `proxy` | Run MCP proxy for agents |
## Examples
### Example 1: Marketing Site from Stitch Designs
A frontend developer uses Stitch to design a startup marketing site, then hands it off to Claude Code for production React components:
```bash
# Preview the Stitch designs locally
npx @_davideast/stitch-mcp serve -p proj_8x7kq2m
# Verify screens look correct at localhost:3000
# Screens: home (hero + features), pricing (3 tiers), about (team bios)
```
With MCP configured, the developer prompts Claude Code:
```
Using the Stitch designs from project proj_8x7kq2m, create production
React components with Tailwind CSS. Map screens:
- home -> /
- pricing -> /pricing
- about -> /about
Use semantic HTML, add responsive breakpoints, and extract shared
components (Navbar, Footer, CTAButton).
```
Claude Code calls `build_site` via MCP with the route mapping, receives the design HTML for each page, and generates a complete Next.js app with `components/Navbar.tsx`, `components/Footer.tsx`, `app/page.tsx`, `app/pricing/page.tsx`, and `app/about/page.tsx` — all matching the original Stitch designs.
### Example 2: Iterating on a Dashboard Design
A product designer creates dashboard screens in Stitch and uses stitch-mcp to iterate between design and code:
```bash
# Browse available screens
npx @_davideast/stitch-mcp view --projects
# Inspect specific screen details
npx @_davideast/stitch-mcp view --project proj_4n9wf3r --screen scr_analytics
# Build the site to see all screens as routes
npx @_davideast/stitch-mcp tool build_site -d '{
"projectId": "proj_4n9wf3r",
"routes": [
{ "screenId": "scr_analytics", "route": "/" },
{ "screenId": "scr_settings", "route": "/settings" },
{ "screenId": "scr_users", "route": "/users" }
]
}'
```
The designer then asks their coding agent: "Take the analytics dashboard from Stitch and add interactive Chart.js graphs for the revenue and user metrics. Keep the exact layout from the design but make the data tables sortable."
The agent fetches the screen HTML via `get_screen_code`, preserves the layout structure, and adds client-side interactivity on top of the design.
## Guidelines
- Run `doctor` after setup to verify authentication and configuration
- Use `snapshot` to save screen state for offline work or version control
- Preview designs with `serve` before handing to agents — faster iteration loop
- Stitch MCP works with VS Code, Cursor, Claude Code, Gemini CLI, Codex, and OpenCode
- Use the interactive browser (`view`) to explore projects before building
- Combine with other design skills (impeccable-design, frontend-design) for polished output
- See [GitHub](https://github.com/davideast/stitch-mcp) and [Google Stitch](https://stitch.google.com) for more
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.