MCP Apps becomes first official MCP UI extension

// 71d agoOPENSOURCE RELEASE

MCP Apps becomes first official MCP UI extension

MCP Apps is now live as the first official MCP extension, letting tools return interactive UIs like forms, dashboards, and visualizations directly inside chat clients. The accompanying walkthrough demonstrates implementation in VS Code, including UI resource registration, SDK wiring, and pausing for user input before continuing agent flow.

// ANALYSIS

This is a meaningful shift from chat-only tool calls to portable agent interfaces that can work across hosts without rebuilding UI logic per client.

–The spec formalizes `ui://` resources and tool metadata patterns, making UI rendering a protocol feature instead of a one-off integration.
–The `ext-apps` SDK creates a shared path for app devs, host devs, and MCP server authors, reducing fragmentation risk.
–Inline interaction plus explicit user-input checkpoints improves trust and control for high-stakes workflows compared with pure text loops.
–Real-world impact will depend on host parity, but the cross-client support trajectory (Claude, ChatGPT, VS Code, Goose) looks strong.

// TAGS

mcp-appsmcpsdkuiagentopen-sourcevscodedevtool

DISCOVERED

71d ago

2026-03-17

PUBLISHED

71d ago

2026-03-17

RELEVANCE

9/ 10

AUTHOR

Burke Holland

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE5h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE6h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE9h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.