All docs

AI Integration

58 MCP tools, Mind + Soul layers, image-to-app pipeline.

Overview

UIX Protocol is designed to be AI-native. Every part of the schema is machine-readable, and AI agents interact with UIX through the Model Context Protocol (MCP).

MCP tools

UIX exposes 58 MCP tools across two servers:

@uix/mcp (34 tools — document operations)

CategoryTools
Documentlist, get, create, update, delete, history
Queryquery, node get, nodes by type, token resolve
Mutationnode set, node insert, node remove, apply diff
Analysismind build, soul annotate, render
Validationvalidate
Version Controlinit, commit, branch create, log, checkout, diff, merge
Collaborationcrdt ops get
Image-to-Appimage analyze, image to generation context

@uix/kernel (24 tools — workflow operations)

CategoryTools
Agentregister, list
Workflowcreate, execute, status
Pipelinetrigger, status
DAGbuild, validate, generate documents
Integrationconfigure, status, test, webhook replay
Backendplan, generate, security audit
QAfunctional tests, full report

Soul layer

Annotate documents with semantic meaning:

typescript
const withSoul = annotateSoul(doc, {
  purpose: 'Authenticates existing users',
  userGoal: 'Get back to work quickly',
  journey: 'onboarding.step-1',
  emotion: 'trust',
});

Mind layer

Build a pre-computed AI reasoning surface:

typescript
const mind = buildMind(doc);
mind.screenType;        // 'authentication'
mind.summary;           // 'Authenticates existing users'
mind.dataRequirements;  // ['auth.email', 'auth.password']
mind.intents;           // ['auth.login', 'auth.setEmail']

// Focused context for one node
const ctx = getMindContext(mind, 'submit-btn');

Image-to-App pipeline

UIX can generate a complete multi-screen app from a design image:

  1. Image analysis — semantic detection of layout, palette, typography, navigation
  2. Design system extraction — tokens derived from the image
  3. Screen planning — 7 domain templates (social, ecommerce, productivity, etc.)
  4. App Flow DAG — complete app topology: screens, states, popups, transitions
  5. Document generation — UIXDocuments for every screen and state
  6. Code generation — multi-platform output from the generated documents
  7. QA validation — automated test generation + coverage analysis

App Flow DAG

The central artifact for autonomous app building — a directed acyclic graph of:

  • Screen nodes — main app screens
  • State nodes — loading, error, empty, success states for each screen
  • Popup nodes — modals, alerts, bottom sheets
  • Transitions — navigation with triggers and animations