Contentrain MCP Server

Contentrain AI

Your AI agent writes content. Contentrain makes sure it doesn't wreck your repo.

Contentrain gives AI agents a governed place to create models, content, translations, and docs — with typed schemas, git-backed review, and deterministic file output that any platform can consume.

Agent produces → System standardizes → Human approves → Any platform consumes

Try it in 30 seconds

npx contentrain init        # create .contentrain/ workspace
npx contentrain serve       # open the local review UI

That's it. You now have a governed content workspace with models, validation, and a local UI — no account, no cloud, no config files.

What it looks like

Before: Hardcoded strings scattered across your codebase — no structure, no translations, no review.

export default function Hero() {
  return (
    <section>
      <h1>Welcome to our platform</h1>
      Start your free trial today
      <button>Get Started</button>
    </section>
  )
}

After: Content lives in .contentrain/, typed and structured. Source files use i18n keys.

export default function Hero() {
  const t = useTranslations()
  return (
    <section>
      <h1>{t('hero.title')}</h1>
      {t('hero.subtitle')}
      <button>{t('hero.cta')}</button>
    </section>
  )
}

// .contentrain/content/marketing/hero/en.json
{
  "cta": "Get Started",
  "subtitle": "Start your free trial today",
  "title": "Welcome to our platform"
}

The normalize flow extracts strings, creates models, and patches your source files — all through reviewable git branches.

How it works

┌─────────────┐     ┌──────────────────┐     ┌──────────────┐
│  AI Agent    │────▶│  MCP (13 tools)  │────▶│ .contentrain/│
│  (decides)   │     │  (enforces)      │     │ (stores)     │
└─────────────┘     └──────────────────┘     └──────┬───────┘
                                                     │
                    ┌──────────────────┐              │
                    │  Review UI / Git │◀─────────────┘
                    │  (human approves)│
                    └──────────────────┘

• Agent decides what content should exist
• MCP enforces schemas, validation, canonical serialization, and git workflow
• Human reviews through branches, PRs, or the local Serve UI
• Output is plain JSON + Markdown — consumed by any language or framework

4 content kinds

27 field types (string, email, url, image, relation, array, object, markdown, ...) with built-in validation.

Use your content anywhere

Content is plain JSON and Markdown. Any language reads it directly.

For TypeScript projects, generate a typed SDK:

npx contentrain generate

import { query, singleton, dictionary, document } from '#contentrain'

const hero    = singleton('hero').locale('en').get()
const posts   = query('blog-post').locale('en').include('author').all()
const labels  = dictionary('ui-labels').locale('tr').get('auth.login')
const article = document('docs').locale('en').bySlug('getting-started')

Works with Nuxt, Next.js, Astro, SvelteKit, Vue, React, Node, Go, Python, Swift, Flutter, and 20+ stacks.

Key features

• Git-native — every write goes through worktree isolation + review branches
• Normalize flow — scan codebase for hardcoded strings → extract → create i18n-ready content → patch source files
• Local-first MCP — 13 tools, stdio transport, works with Claude Code, Cursor, Windsurf, or any MCP client
• Canonical serialization — sorted keys, deterministic output, clean git diffs, conflict-free parallel edits
• Agent rules & skills — behavioral policies and step-by-step workflows ship as npm packages
• Serve UI — local web dashboard for browsing models, content, validation, and normalize status
• Framework-agnostic — MCP doesn't know your framework. Agent + skills handle stack-specific logic

Packages