This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.
npx skills add https://github.com/tldraw/tldraw --skill migrate-oai-app
Migrate existing OpenAI Apps SDK applications to the MCP Apps SDK (@modelcontextprotocol/ext-apps). The MCP Apps SDK provides a standardized, open protocol for interactive UIs in conversational clients.
npm install, pnpm add, yarn add) instead of manually writing version numbers. This lets the package manager resolve the latest compatible versions. Never specify version numbers from memory.Clone the SDK repository for complete migration documentation and working examples:
git clone --branch "v$(npm view @modelcontextprotocol/ext-apps version)" --depth 1 https://github.com/modelcontextprotocol/ext-apps.git /tmp/mcp-ext-apps
Read the migration reference guide with "before/after" mapping tables: /tmp/mcp-ext-apps/docs/migrate_from_openai_apps.md
Read JSDoc documentation directly from /tmp/mcp-ext-apps/src/*:
| File | Contents |
| ---------------------- | ---------------------------------------- |
| src/app.ts | App class, handlers, lifecycle |
| src/server/index.ts | registerAppTool, registerAppResource |
| src/spec.types.ts | Type definitions |
| src/react/useApp.tsx | useApp hook for React apps |
| src/react/use*.ts* | Other use* hooks for React apps |
See /tmp/mcp-ext-apps/examples/basic-server-{framework}/ for basic SDK usage examples organized by front-end framework:
| Template | Key Files |
| ------------------------- | --------------------------------------------------- |
| basic-server-vanillajs/ | server.ts, src/mcp-app.ts, mcp-app.html |
| basic-server-react/ | server.ts, src/mcp-app.tsx (uses useApp hook) |
| basic-server-vue/ | server.ts, src/App.vue |
| basic-server-svelte/ | server.ts, src/App.svelte |
| basic-server-preact/ | server.ts, src/mcp-app.tsx |
| basic-server-solid/ | server.ts, src/mcp-app.tsx |
MCP Apps HTML is served as an MCP resource, not as a web page, and runs in a sandboxed iframe with no same-origin server. Every origin must be declared in CSP—including the origin serving your JS/CSS bundles (localhost in dev, your CDN in production). Missing origins fail silently.
Before writing any migration code, build the app and investigate all origins it references:
Document your findings as three lists, and note for each origin whether it's universal, dev-only, or prod-only:
If no origins are found, the app may not need custom CSP domains.
MCP clients make cross-origin requests. If using Express, app.use(cors()) handles this.
For raw HTTP servers, configure standard CORS and additionally:
mcp-session-id, mcp-protocol-version, last-event-idmcp-session-idUse registerAppTool() and registerAppResource() helpers instead of raw server.registerTool() / server.registerResource(). These helpers handle the MCP Apps metadata format automatically.
See /tmp/mcp-ext-apps/docs/migrate_from_openai_apps.md for server-side mapping tables.
The fundamental paradigm shift: OpenAI uses a synchronous global object (window.openai.toolInput, window.openai.theme) that's pre-populated before your code runs. MCP Apps uses an App instance with async event handlers.
Key differences:
App instance and register handlers (ontoolinput, ontoolresult, onhostcontextchanged) before calling connect(). (Events may fire immediately after connection, so handlers must be registered first.)app.ontoolinput for window.openai.toolInput, app.ontoolresult for window.openai.toolOutput.app.getHostContext().For React apps, the useApp hook manages this lifecycle automatically—see basic-server-react/ for the pattern.
See /tmp/mcp-ext-apps/docs/migrate_from_openai_apps.md for client-side mapping tables.
These OpenAI features don't have MCP equivalents yet:
Server-side:
| OpenAI Feature | Status/Workaround |
|----------------|-------------------|
| _meta["openai/toolInvocation/invoking"] / _meta["openai/toolInvocation/invoked"] | Progress indicators not yet available |
| _meta["openai/widgetDescription"] | Use app.updateModelContext() for dynamic context |
Client-side:
| OpenAI Feature | Status/Workaround |
|----------------|-------------------|
| window.openai.widgetState / setWidgetState() | Use localStorage or server-side state |
| window.openai.uploadFile() / getFileDownloadUrl() | File operations not yet available |
| window.openai.requestModal() / requestClose() | Modal management not yet available |
| window.openai.view | Not yet available |
Slow down and carefully follow each item in this checklist:
| Pattern | Indicates |
| --------------------------- | ----------------------------------------------------------------- |
| "openai/ | Old metadata keys → _meta.ui.* |
| text/html+skybridge | Old MIME type → RESOURCE_MIME_TYPE constant |
| text/html;profile=mcp-app | New MIME type, but prefer RESOURCE_MIME_TYPE constant |
| _domains" or _domains: | snake_case CSP → camelCase (connect_domains → connectDomains) |
| Pattern | Indicates |
| -------------------------- | --------------------------------------------------------- |
| window.openai.toolInput | Old global → params.arguments in ontoolinput handler |
| window.openai.toolOutput | Old global → params.structuredContent in ontoolresult |
| window.openai | Old global API → App instance methods |
registerAppResource() CSP config. Every origin from the CSP investigation (universal, dev-only, prod-only) must be included in the CSP config—MCP Apps HTML runs in a sandboxed iframe with no same-origin server. If an origin was not included in the CSP config, add it now.Test the migrated app with the basic-host example:
# Terminal 1: Build and run your server
npm run build && npm run serve
# Terminal 2: Run basic-host (from cloned repo)
cd /tmp/mcp-ext-apps/examples/basic-host
npm install
SERVERS='["http://localhost:3001/mcp"]' npm run start
# Open http://localhost:8080
Once the app loads in basic-host, confirm:
ontoolinput handler fires with tool argumentsontoolresult handler fires with tool resultGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take tldraw/migrate-oai-app from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npm, yarn, pnpm.
Without those the skill loads but fails at the first command.