Develop ChatGPT apps with interactive React widgets using mcp-use and OpenAI Apps SDK. Guidance covers app scope, server tools, shared state, and display settings. This skill is deprecated and points users to mcp-app-builder.
DEPRECATED: This skill has been replaced by `mcp-app-builder`. Check if `mcp-app-builder` is available in the skills folder. If not, install it: `npx skills install mcp-use/mcp-use --skill mcp-app-builder` Use `mcp-app-builder` instead of this skill. Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT apps, building MCP servers with widgets, defining React widgets, working with Apps SDK, or when user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development.
Review the instructions the agent will receive before you install.
Build ChatGPT apps with interactive widgets using mcp-use. Zero-config widget development with automatic registration and built-in React hooks.
The app is consumed by two users at once: the human and the ChatGPT LLM. They collaborate through the widget -- the human interacts with it, the LLM sees its state. The widget is your shared surface.
// Server
import { MCPServer, widget, text, object } from "mcp-use/server";
server.tool({ name: "...", schema: z.object({...}), widget: { name: "widget-name" } },
async (input) => widget({ props: {...}, output: text("...") })
);
// Widget (resources/widget-name.tsx)
import { McpUseProvider, useWidget, type WidgetMetadata } from "mcp-use/react";
export const widgetMetadata: WidgetMetadata = { description: "...", props: z.object({...}) };
export default function MyWidget() {
const { props, isPending, callTool, sendFollowUpMessage, state, setState, theme } = useWidget();
if (isPending) return <McpUseProvider autoSize><div>Loading...</div></McpUseProvider>;
return <McpUseProvider autoSize><div>{/* UI */}</div></McpUseProvider>;
}
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Coordinate large research or generation tasks across a model team. An orchestrator plans and checks the work, workers execute subtasks in parallel, and an advisor reviews the plan and draft before the results are combined.
Investigate why a file or function exists using local Git history. Trace its introduction, later edits, authorship, and files often changed alongside it, then summarize likely intent and change risks while distinguishing evidence from inference.
Inspect Python and JavaScript dependency files for missing version constraints, duplicate entries, conflicting exact versions, and outdated Python compatibility packages. Get plain-language explanations and focused repair suggestions, with offline checks by default.
Simulate readers encountering a draft for the first time to see whether they open it, where their attention fades, and what they remember. Receive reader comments alongside the text without rewrites or suggested fixes.
Build MCP servers that let AI access actions and data using mcp-use. The guide covers project setup, reusable prompts, interactive React interfaces, authentication, error handling, and deployment, with reference files for each area.
A deprecated guide to building MCP servers with mcp-use, covering callable actions, data resources, reusable prompts, and interactive widgets. It includes design references and code examples, and directs users to the replacement skill, mcp-app-builder.