Build ChatGPT apps with MCP servers on Cloudflare Workers, extending ChatGPT with custom tools and interactive HTML/JS widgets.
Works with
Implements JSON-RPC 2.0 MCP protocol with tool registration, execution, and widget resource serving via ASSETS binding
Requires CORS allowlist for https://chatgpt.com , ui://widget/ URI prefix for widgets, and text/html+skybridge MIME type
Prevents 14 documented issues including CORS blocks, widget 404s, MIME type misconfigurations, SSE timeouts, and Next.js
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionopenai-apps-mcpExecute the skills CLI command in your project's root directory to begin installation:
Fetches openai-apps-mcp from jezweb/claude-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate openai-apps-mcp. Access via /openai-apps-mcp in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
697
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
697
stars
Status: Production Ready
Last Updated: 2026-01-21
Dependencies: cloudflare-worker-base, hono-routing (optional)
Latest Versions: @modelcontextprotocol/[email protected], [email protected], [email protected], [email protected]
Build ChatGPT Apps using MCP (Model Context Protocol) servers on Cloudflare Workers. Extends ChatGPT with custom tools and interactive widgets (HTML/JS UI rendered in iframe).
Architecture: ChatGPT → MCP endpoint (JSON-RPC 2.0) → Tool handlers → Widget resources (HTML)
Status: Apps available to Business/Enterprise/Edu (GA Nov 13, 2025). MCP Apps Extension (SEP-1865) formalized Nov 21, 2025.
npm create cloudflare@latest my-openai-app -- --type hello-world --ts --git --deploy false
cd my-openai-app
npm install @modelcontextprotocol/[email protected] [email protected] [email protected]
npm install -D @cloudflare/[email protected] [email protected]
{
"name": "my-openai-app",
"main": "dist/index.js",
"compatibility_flags": ["nodejs_compat"], // Required for MCP SDK
"assets": {
"directory": "dist/client",
"binding": "ASSETS" // Must match TypeScript
}
}
src/index.ts)import { Hono } from 'hono';
import { cors } from 'hono/cors';
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { ListToolsRequestSchema, CallToolRequestSchema } from '@modelcontextprotocol/sdk/types.js';
const app = new Hono<{ Bindings: { ASSETS: Fetcher } }>();
// CRITICAL: Must allow chatgpt.com
app.use('/mcp/*', cors({ origin: 'https://chatgpt.com' }));
const mcpServer = new Server(
{ name: 'my-app', version: '1.0.0' },
{ capabilities: { tools: {}, resources: {} } }
);
// Tool registration
mcpServer.setRequestHandler(ListToolsRequestSchema, async () => ({
tools: [{
name: 'hello',
description: 'Use this when user wants to see a greeting',
inputSchema: {
type: 'object',
properties: { name: { type: 'string' } },
required: ['name']
},
annotations: {
openai: { outputTemplate: 'ui://widget/hello.html' } // Widget URI
}
}]
}));
// Tool execution
mcpServer.setRequestHandler(CallToolRequestSchema, async (request) => {
if (request.params.name === 'hello') {
const { name } = request.params.arguments as { name: string };
return {
content: [{ type: 'text', text: `Hello, ${name}!` }],
_meta: { initialData: { name } } // Passed to widget
};
}
throw new Error(`Unknown tool: ${request.params.name}`);
});
app.post('/mcp', async (c) => {
const body = await c.req.json();
const response = await mcpServer.handleRequest(body);
return c.json(response);
});
app.get('/widgets/*', async (c) => c.env.ASSETS.fetch(c.req.raw));
export default app;
src/widgets/hello.html)<!DOCTYPE html>
<html>
<head>
<style>
body { margin: 0; padding: 20px; font-family: system-ui; }
</style>
</head>
<body>
<div id="greeting">Loading...</div>
<script>
if (window.openai && window.openai.getInitialData) {
const data = window.openai.getInitialData();
document.getElementById('greeting').textContent = `Hello, ${data.name}! 👋`;
}
</script>
</body>
</html>
npm run build
npx wrangler deploy
npx @modelcontextprotocol/inspector https://my-app.workers.dev/mcp
CORS: Must allow https://chatgpt.com on /mcp/* routes
Widget URI: Must use ui://widget/ prefix (e.g., ui://widget/map.html)
MIME Type: Must be text/html+skybridge for HTML resources
Widget Data: Pass via _meta.initialData (accessed via window.openai.getInitialData())
Tool Descriptions: Action-oriented ("Use this when user wants to...")
ASSETS Binding: Serve widgets from ASSETS, not bundled in worker code
SSE: Send heartbeat every 30s (100s timeout on Workers)
This skill prevents 14 documented issues:
Error: Access to fetch blocked by CORS policy
Fix: app.use('/mcp/*', cors({ origin:
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
jezweb/claude-skills
jezweb/claude-skills
jezweb/claude-skills
aradotso/trending-skills
davila7/claude-code-templates
intellectronica/agent-skills
openai-apps-mcp reduced setup friction for our internal harness; good balance of opinion and flexibility.
Registry listing for openai-apps-mcp matched our evaluation — installs cleanly and behaves as described in the markdown.
openai-apps-mcp has been reliable in day-to-day use. Documentation quality is above average for community skills.
Useful defaults in openai-apps-mcp — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
openai-apps-mcp is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
openai-apps-mcp fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
Keeps context tight: openai-apps-mcp is the kind of skill you can hand to a new teammate without a long onboarding doc.
We added openai-apps-mcp from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in openai-apps-mcp — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Keeps context tight: openai-apps-mcp is the kind of skill you can hand to a new teammate without a long onboarding doc.
showing 1-10 of 45