1. Conduid
  2. Science
  3. io.github.decantr-ai/mcp-server
MCP server · Science

io.github.decantr-ai/mcp-server

Design intelligence for AI-generated UI. Essence spec, registry, drift detection, and critique.

Unclaimed science
37Low

Scored 4 months ago · breakdown

About io.github.decantr-ai/mcp-server

io.github.decantr-ai/mcp-server is an MCP server in the Science category: design intelligence for AI-generated UI. Essence spec, registry, drift detection, and critique. It has been installed 0 times through Conduid.

Install

Claude Code
claude mcp add io-github-decantr-ai-mcp-server -- npx -y @decantr/mcp-server
npx
npx -y @decantr/mcp-server

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about io.github.decantr-ai/mcp-server

Powered by Claude · Grounded in docs

I know everything about io.github.decantr-ai/mcp-server. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • ·Scoped permissionsNot checked yet.

README

Decantr

Design intelligence, governance, and verification for AI-generated UI.

Decantr is the contract layer between product intent and AI-generated implementation. It gives coding assistants three things they don't have on their own — structured design inputs, registry-backed UI knowledge, and scoped context files — so they build coherent product surfaces instead of improvising screen by screen. Think of it as OpenAPI for AI-generated UI: the model still writes the code, but Decantr defines the shape, vocabulary, and checks around it.

AI generates the interface. Decantr keeps the outcome aligned.

Pick your path

Path Use when Start with
Greenfield blueprint  ⭐ New project, published app composition as the starting point decantr new my-app --blueprint=<id> --workflow=greenfield --adoption=decantr-css
Greenfield contract-only New project or repo that wants Decantr governance but no blueprint/runtime takeover decantr init --workflow=greenfield --adoption=contract-only
Brownfield adoption Attaching Decantr to an existing Angular/React/Vue/etc. project decantr analyze, then decantr init --existing --adoption=contract-only
Hybrid composition Layering sections, themes, or features into an attached project decantr add/remove, decantr theme switch, decantr registry

Greenfield blueprint

1. Scaffold from a blueprint

npx @decantr/cli new my-app --blueprint=agent-marketplace
cd my-app

A blueprint is a published app composition — theme, sections, pages, layouts, voice, and personality. Try agent-marketplace, terminal-dashboard, or portfolio to start, or run decantr search to browse the full catalog.

Adapter availability. react-vite and next-app are runnable starter adapters in this wave. Other contract targets remain valid Decantr targets but initialize through generic-web contract-only mode — Decantr writes the contract, you own the runtime.

2. What just got generated

my-app/
├── decantr.essence.json     # the durable contract: theme, sections, routes, features
├── DECANTR.md               # methodology primer your AI assistant reads first
├── .decantr/context/
│   ├── scaffold.md          # full app overview: topology, voice, personality
│   └── section-*.md         # per-section spec: shell, patterns, spacing
└── src/styles/
    ├── tokens.css           # CSS variables from the theme
    ├── treatments.css       # shared visual treatment classes
    └── decorators.css       # theme-specific decorator classes

Decantr produces the contract. Your AI assistant produces the implementation against it.

3. Hand it to your AI assistant

Open the project in Claude Code, Cursor, Windsurf, or any AI-aware editor. Your assistant reads DECANTR.md first for the methodology, then loads section context files on demand as it works through each part of the app. The split keeps the assistant focused on the right scope at the right time.

4. Make your first change and verify

# Edit decantr.essence.json — add a section, swap the theme, etc.
decantr refresh   # regenerate context files from the updated essence
decantr check     # verify the code matches the new contract

refresh keeps the generated context files in sync with the essence. check runs the guard rules and tells you exactly where the code drifted from the contract. decantr audit is a broader pass when you want a full report.

Starting from a different point? See the full workflow model.


The model

Decantr separates design governance into two layers:

  • DNA — durable visual and system axioms: theme, spacing, motion, accessibility, personality.
  • Blueprint — product topology: sections, page routes, shells, layouts, features.

That split matters because not every change should be treated the same way. A theme swap or accessibility regression is different from adding an auxiliary section or reshaping a route map. Decantr lets governance be strict where it should be strict (DNA, errors by default) and flexible where it should be flexible (Blueprint, warnings only).

Canonical shapes live in the published schemas; the command-level flow is in the workflow model.

Surfaces

Surface What it does
CLI Scaffold new apps, initialize existing projects, refresh derived context, search registry content, and run checks/audits
MCP server Exposes Decantr directly to AI tools — essence reads, registry resolution, context reads, pack compilation, drift checks, critique, and audit
Hosted registry/API Browse and search public content, read intelligence summaries, compile execution packs, critique files, and audit projects
Verifier Shared audit and critique engine with schema-backed reports
Showcase apps Audited benchmark corpus and verification targets for Decantr-generated scaffolds

Packages

Package Role
@decantr/essence-spec Essence schemas, validation, migration, and TypeScript types
@decantr/registry Registry contracts, schemas, content utilities, and API client surfaces
@decantr/css Framework-agnostic CSS atom runtime
@decantr/core Execution-pack compiler primitives and shared Decantr utilities
@decantr/verifier Shared audit, critique, and report-schema engine
@decantr/mcp-server MCP delivery surface for assistants and agent tooling
@decantr/cli Local scaffold, registry, audit, and maintenance workflows
@decantr/vite-plugin Experimental local guard feedback overlay for Vite

Full release/support status lives in docs/reference/package-support-matrix.md.

Repo layout

Path Role
apps/api Hosted API for registry, packs, critique, audit, auth, org, and billing-adjacent flows
apps/registry Next.js registry portal and internal dogfood surface
apps/showcase-host Shared Vite host for live blueprint showcase capsules
apps/showcase/ Showcase manifest and verification reports used by the API and registry
packages/* Core Decantr packages and supporting runtime surfaces
docs/ Public docs, audits, architecture notes, schemas, and runbooks
scripts/ Audit, release, showcase, schema, and packaging automation

Showcase capsule architecture is documented in docs/reference/showcase-host.md.

Development

Requires Node.js >=20 and pnpm >=9.

pnpm install
pnpm build
pnpm test
pnpm lint
pnpm audit:public-api
pnpm audit:registry-dogfood
pnpm showcase:verify:shortlist

More CLI

Intent and discovery:

decantr magic "AI chatbot with a bold terminal-inspired workspace"
decantr search dashboard
decantr suggest leaderboard

Brownfield adoption:

decantr analyze
decantr init --existing --yes --adoption=contract-only

Registry and verification:

decantr registry summary       --namespace @official --json
decantr registry compile-packs decantr.essence.json --write-context
decantr registry critique-file src/pages/Home.tsx  --namespace @official --json
decantr registry audit-project --namespace @official --json
decantr showcase verification  --json

Links

Contributing

Contributions are welcome. The most useful repo context lives in docs/ — especially the architecture notes, audits, runbooks, and package support matrix.

License

MIT. The source repositories are MIT licensed; hosted services such as the registry and API may publish separate service terms without changing the source-code license.

README mirrored from the source repository 4 months ago. The original is authoritative.

Questions

About io.github.decantr-ai/mcp-server

How do I install io.github.decantr-ai/mcp-server?

Run claude mcp add io-github-decantr-ai-mcp-server -- npx -y @decantr/mcp-server, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is io.github.decantr-ai/mcp-server safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is io.github.decantr-ai/mcp-server still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.