agentic-ux
daniel-albinsson/agentic-uxAgentic 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}, agentic-ux://library/full, and agentic-ux://enforcement) so agents can attach specs, and the Agentic Kit enforcement notes, 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#mcp
Score: 100/100
Handshake verified by our own probe.
Tools · 4
List all available Agentic UX design pattern slugs. Prefer resources/list for MCP-native discovery.
Retrieve the full Agentic UX pattern specification for a given slug. Prefer resource agentic-ux://patterns/{slug} when attaching context.
Retrieve the complete Agentic UX pattern library as a single document (llms-full.txt). Prefer resource agentic-ux://library/full when attaching context.
Return a structured Agentic UX lifecycle audit kit for one agent flow. Inspect the user's product, then fill the returned report schema with evidence. Does not score automatically : the calling agent …
Resources · 13
Complete pattern library as a single document (llms-full.txt). Prefer this resource over get_full_pattern_library when browsing MCP resources.
agentic-ux://library/full
Where Agentic UX patterns become enforceable checks for eve (Vercel) agents: Aletheia portrait, authority-diff CI gate, policy packs.
agentic-ux://enforcement
Agentic UX pattern specification for Intent-First Interface
agentic-ux://patterns/intent-first
Agentic UX pattern specification for Intent Preview
agentic-ux://patterns/intent-preview
Agentic UX pattern specification for Clarifying Questions
agentic-ux://patterns/clarifying-questions
Agentic UX pattern specification for Autonomy Dial
agentic-ux://patterns/autonomy-dial
Agentic UX pattern specification for Explainable Rationale
agentic-ux://patterns/explainable-rationale
Agentic UX pattern specification for Progress Ledger
agentic-ux://patterns/progress-ledger
Agentic UX pattern specification for Action Audit & Undo
agentic-ux://patterns/action-audit
Agentic UX pattern specification for Escalation Pathway
agentic-ux://patterns/escalation-pathway
Agentic UX pattern specification for Generative UI
agentic-ux://patterns/generative-ui
Agentic UX pattern specification for Return Moment
agentic-ux://patterns/return-moment
Agentic UX pattern specification for Sandbox Preview
agentic-ux://patterns/sandbox-preview
Prompts · 2
Start a structured Agentic UX lifecycle audit. Pairs with the review_agent_flow tool.
Implement one Agentic UX pattern with spec-first guidance from the pattern resource.
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://www.agentic-ux.com/api/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"agentic-ux": {
"url": "https://www.agentic-ux.com/api/mcp",
"transport": "http"
}
}
}