Cre8 app factory
The cre8 plugin

An MCP server plus five skills that teach an agent to actually use it.

A live tool call finds the right component. A skill is what stops an agent from stopping there — composition rules, token architecture, and framework-specific conventions the MCP intentionally doesn’t restate.

Skills

Five skills, bundled as one plugin

Installed together on Claude Code, Cowork, Codex CLI, and Gemini CLI — lookup, generation, brand theming, and live interactive surfaces.

cre8-a2ui

Web Components guidance for vanilla JS/HTML and Lit — which component a job calls for, and the token architecture underneath it.

cre8-a2ui-react

The same judgment, for React — 72 components with props, patterns, and conventions specific to the React wrappers.

cre8-mcp-ui

Serves Cre8 components as live, interactive UI from a Python FastMCP server — a tool call that returns a working surface, not a text reply.

cre8-theming

Extracts a brand's colors, type and shape from a website, a picture, or a Design.md, and turns it into a seed-token override.

cre8-mcp-app-workflow

Coordinates the whole branded-app build — theming, then integration, then per-host rendering checks — handing each stage’s artifacts to the next.

Agents and workflow

Three specialists, one workflow that drives them

Building a branded MCP App is three jobs with hard handoffs between them. Each runs as its own agent that returns to the main session with named artifacts, so the next stage starts from evidence rather than a summary.

cre8-brand-themer

Extracts and verifies the brand. Returns theme.css and a handoff recording source evidence, inferred values, and anything it could not confirm.

cre8-mcp-app-builder

Builds the MCP server and embedded UI on the ext-apps bridge for both Claude Desktop and ChatGPT, keeping host extensions isolated and capability-gated.

cre8-mcp-render-debugger

Reproduces the failing tool call and traces it end to end — connection, resource URI, CSP, bridge init, component upgrade, theme cascade, callback round trip.

cre8:workflow-themed-mcp-app

Runs all three as a deterministic workflow in Claude Code: one verification lane per host, and an independent auditor that downgrades any pass it cannot show was observed.

Why the auditor matters. A local harness passing is not the desktop app working, and the difference is invisible in a summary. Every scenario the debugger reports carries how it was observed and what evidence backs it; a separate agent that did not do the work then tries to refute each pass claim. What survives is reported as passing. What doesn’t is marked unverified — which is the honest answer, and the one you can act on.

Claude Code · run the workflow
// Ask for it by name — workflows need an explicit opt-in
> run the cre8:workflow-themed-mcp-app workflow

// Optional args
{
  "brandSource": "https://example.com",
  "hosts": ["Claude Desktop", "ChatGPT"],
  "entry": "theme"  // or "integrate" | "debug"
}
See it run

The same branded app, verified in both hosts

One Starbucks-themed MCP App, served by one server and rendering in both desktop hosts — the part a screenshot can’t show.

Claude Desktop · MCP App
Rendering in ClaudeA tool call returning a live interactive surface, themed from the extracted brand — picking a size and a milk updates the order in place.
ChatGPT · MCP App
Rendering in ChatGPTThe same server and the same UI resource in a second host, with the host-specific extensions capability-gated rather than forked.
Install

One bundle, four hosts

Claude Code
// MCP server, five skills, three agents, one workflow
claude plugin install cre8@tmorrow_ai
Codex CLI
// Same bundle, Codex’s own plugin format
codex plugin add cre8@tmorrow_ai
Gemini CLI
// Same bundle, as a Gemini extension
gemini extensions install https://github.com/tmorrowdev/cre8-gemini-extension.git

On Cursor, Windsurf, VS Code, OpenCode, or any other MCP-compatible tool? Those don’t have an equivalent plugin mechanism for the skills yet. But @tmorrow/cre8-mcp is the same standard MCP server either way — drop it into that tool’s MCP config and every tool works identically. The composition guidance the skills carry is still reachable through the MCP itself: call cre8_guide and get_composition the same way an agent with the skills installed would.