@modelcontextprotocol/ext-apps

Enables MCP servers to define and render interactive user interfaces directly within conversational AI clients (Claude, etc.) by extending the MCP protocol with UI schema definitions. Works by allowing servers to declare UI components (forms, buttons, displays) that clients interpret and render natively, maintaining the request-response contract of MCP while adding a presentation layer for rich interactions beyond text.

Provides a TypeScript/JavaScript SDK for declaring UI components (forms, buttons, text displays, etc.) using JSON schema definitions that are validated and serialized for transmission to MCP clients. The SDK includes type-safe builders and validators that ensure UI schemas conform to the MCP Apps specification before being sent, catching structural errors at development time rather than runtime.

Enables MCP servers to define forms with typed fields (text inputs, dropdowns, checkboxes, etc.), client-side validation rules, and submission handlers that process user input. When users submit forms in the client, the server receives structured, validated data back through the MCP protocol, allowing servers to react to user interactions and update UI state accordingly.

Allows MCP servers to manage UI state on the client side by sending UI update messages that modify rendered components reactively. Servers can update form values, show/hide elements, enable/disable buttons, or change display content without requiring a full UI re-render, enabling responsive interactions and progressive disclosure patterns within conversational clients.

Implements the MCP protocol extension mechanism that allows servers to advertise UI capabilities and clients to declare support for the Apps extension. Uses capability negotiation during the MCP initialization handshake to ensure both server and client support UI features before attempting to render interactive components, preventing errors when clients don't support the extension.

Manages UI context and state across multiple conversation turns by allowing servers to maintain references to previously rendered UI components and update them based on new user messages. Servers can track which UI elements were shown, what data was submitted, and how to evolve the UI as the conversation progresses, enabling coherent multi-turn interactions.

Provides UI components for displaying structured data, tables, lists, and formatted text that render richly in conversational clients. Servers can format data for display using predefined component types (tables, code blocks, formatted lists) that clients render with appropriate styling and layout, improving readability compared to plain text output.

Enables servers to define clickable buttons and action components that trigger server-side handlers when clicked. Buttons can be configured with labels, icons, and action types, and when clicked, send messages back to the server that invoke corresponding handler functions, enabling direct user-driven interactions without requiring form submissions.

Provides mechanisms for servers to send error messages, warnings, and informational feedback to users through the UI layer. Servers can display validation errors, operation failures, or status messages that render appropriately in the client (e.g., error dialogs, inline validation messages), improving user experience by providing clear feedback on server-side operations.

Provides TypeScript/JavaScript patterns, utilities, and example implementations for building MCP servers with UI support. Includes base classes, middleware, and helper functions that simplify common tasks like defining tools with UI, handling form submissions, and managing state, reducing boilerplate and accelerating development of UI-enabled MCP servers.