stitch-sdk-usage（stitch SDK 使用）

Using the Stitch SDK

The Stitch SDK provides a TypeScript interface for Google Stitch, an AI-powered UI generation service.

Installation

npm install @google/stitch-sdk

Environment Variables

export STITCH_API_KEY="your-api-key"

Quick Start

import { stitch } from '@google/stitch-sdk';

const project = await stitch.createProject("My App");
const screen = await project.generate("A settings page with dark theme");
const html = await screen.getHtml();     // download URL for the HTML
const imageUrl = await screen.getImage(); // download URL for the screenshot

The stitch singleton reads STITCH_API_KEY from the environment and connects on first use — no setup code required.

Working with Projects

import { stitch } from '@google/stitch-sdk';

// List all projects
const projects = await stitch.projects();

// Reference a project by ID (no network call)
const project = stitch.project("4044680601076201931");

// Create a new project
const newProject = await stitch.createProject("My App");

Design Systems

// Create a design system for a project
const ds = await project.createDesignSystem({ displayName: "My Theme" });

// List design systems
const systems = await project.listDesignSystems();

// Reference by ID (no network call)
const dsRef = project.designSystem("existing-asset-id");

// Update a design system
const updated = await ds.update({ displayName: "Updated Theme" });

// Apply to screens (requires SelectedScreenInstance objects from project.data.screenInstances)
const screens = await ds.apply([
  { id: "instance-id", sourceScreen: "projects/123/screens/456" }
]);

Uploading Images

Upload an existing image file (PNG, JPG, JPEG, WEBP) to create a screen directly from a mockup or asset.

import { stitch } from '@google/stitch-sdk';

const project = stitch.project("your-project-id");

// Upload a local image file
const [screen] = await project.uploadImage('./mockup.png', {
  title: 'Home Screen',
});

console.log(screen.id);
const html = await screen.getHtml();
const imageUrl = await screen.getImage();

The method reads the file from disk and posts it directly to the Stitch REST API — no output token constraints apply (unlike agent-driven MCP calls).

Supported formats: .png, .jpg, .jpeg, .webp

Options:

Throws StitchError with codes: NOT_FOUND (file not found), UNKNOWN_ERROR (unsupported format or upload failure), AUTH_FAILED (invalid API key).

Generating and Iterating on Screens

// Generate a new screen from a prompt
const screen = await project.generate("Login page with email and password fields");

// Edit an existing screen
const edited = await screen.edit("Make the background dark and add a subtitle");

// Generate variants of a screen
const variants = await screen.variants("Try different color schemes", {
  variantCount: 2,
  creativeRange: "EXPLORE",
  aspects: ["COLOR_SCHEME", "LAYOUT"],
});

Retrieving Screen Assets

// Get screen HTML download URL
const html = await screen.getHtml();

// Get screen screenshot download URL
const imageUrl = await screen.getImage();

Both methods use cached data from the generation response when available, falling back to an API call when needed.

Dynamic Tool Client (for agents)

For agents and orchestration scripts that forward JSON payloads to MCP tools:

import { StitchToolClient } from '@google/stitch-sdk';

const client = new StitchToolClient(); // reads STITCH_API_KEY from env
const tools = await client.listTools();
const result = await client.callTool("generate_screen_from_text", {
  projectId: "123", prompt: "A login page"
});
await client.close();

Error Handling

All SDK methods throw StitchError on failure. Use try/catch:

import { stitch, StitchError } from '@google/stitch-sdk';

try {
  const project = stitch.project("bad-id");
  await project.screens();
} catch (e) {
  if (e instanceof StitchError) {
    console.log(e.code);        // "AUTH_FAILED", "NOT_FOUND", etc.
    console.log(e.message);     // Human-readable description
    console.log(e.recoverable); // Whether retrying might succeed
  }
}

Error codes: AUTH_FAILED, NOT_FOUND, PERMISSION_DENIED, RATE_LIMITED, NETWORK_ERROR, VALIDATION_ERROR, UNKNOWN_ERROR

API Reference

Stitch Class

Project Class

deviceType: "MOBILE" | "DESKTOP" | "TABLET" | "AGNOSTIC"

uploadImage supported formats: .png .jpg .jpeg .webp

DesignSystem Class

Screen Class

modelId: "GEMINI_3_PRO" | "GEMINI_3_FLASH"

StitchToolClient (for agents)

Explicit Configuration

import { Stitch, StitchToolClient } from '@google/stitch-sdk';

const client = new StitchToolClient({
  apiKey: "your-api-key",
  baseUrl: "https://stitch.googleapis.com/mcp",
  timeout: 300_000,
});

const sdk = new Stitch(client);
const projects = await sdk.projects();