# Agentic UX MCP **Agentic UX MCP** gives coding agents a machine-readable reference for designing interfaces where AI delegates work and users stay in control. It ships **11 lifecycle patterns** — from intent preview and autonomy dials to progress ledgers and return moments — each with anatomy, do/avoid guidance, limitations, and production examples. Patterns are available as **MCP resources** (`agentic-ux://patterns/{slug}` and `agentic-ux://library/full`) so agents can attach specs directly to context. For reviews, **`review_agent_flow`** returns a structured audit kit: lifecycle rubric, empty report schema, and prioritized pattern recommendations for a specific agent flow. **Prompts** provide guided entry points for audits and spec-first implementation. **Best for:** designers and builders shipping long-running agents in Cursor, Replit, research tools, and support automation — anywhere users delegate work and need visibility, consent, and recovery. **No configuration required.** Docs: [agentic-ux.com/guide](https://agentic-ux.com/guide)
How to connect
https://server.smithery.ai/daniel-albinsson/agentic-ux/mcpcurl -X POST https://server.smithery.ai/daniel-albinsson/agentic-ux/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'