Contentrain MCP is a content operations engine that lets AI agents extract, create, manage, and govern structured content from codebases through 15 tools, enforcing schemas, git workflows, and canonical serialization.

Project Setup

• Initialize a .contentrain/ workspace with contentrain_init (auto-detects stack, domains, locales)

• Scaffold full project templates (blog, landing, docs, ecommerce, saas, i18n, mobile) with contentrain_scaffold

Model Management

• Create/update content models (collection, singleton, document, dictionary) with contentrain_model_save, supporting 27 field types

• Delete models and associated content with contentrain_model_delete

Content Operations

• Save, list/filter, and delete content entries across all model types with contentrain_content_save, contentrain_content_list, and contentrain_content_delete

• Batch operations (copy locale, update status, bulk delete) with contentrain_bulk

Content Normalization

• Scan source code for hardcoded strings with contentrain_scan (modes: graph, candidates, summary)

• Apply normalize operations with contentrain_apply — extract strings into content files or patch source files with i18n expressions (supports dry-run preview)

Validation & Inspection

• Validate content against schemas with contentrain_validate, detecting missing fields, type mismatches, broken relations, secret leaks, and i18n parity issues; with optional auto-fix

• Get full project status with contentrain_status, model schemas with contentrain_describe, and file format specs with contentrain_describe_format

Git Workflow

• All write operations auto-commit to git branches; push review branches for human PR approval with contentrain_submit

• Framework-agnostic with canonical serialization for clean diffs and conflict-free parallel edits

Allows managing and consuming structured content within Astro web projects.

Provides a framework-agnostic way to manage and deliver content to Expo applications.

Supports content delivery and management for Flutter mobile and web apps.

Enforces a mandatory Git-based workflow for content versioning, branch-backed reviews, and auditability.

Enables Kotlin applications to consume governed content stored within the repository.

Utilizes Markdown for content storage and platform-independent delivery.

Supports consuming governed content within Node.js environments.

Facilitates structured content management and consumption for Nuxt applications.

Allows Python applications to directly consume governed content as plain JSON or Markdown.

Provides tools for managing and querying content within React-based applications.

Enables Rust applications to consume repository-native content.

Supports delivering governed content to Swift applications on any platform.

Generates a type-safe SDK for querying governed content within TypeScript projects.

Agent extracts or updates content → Contentrain standardizes → Human reviews → Any platform consumes

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

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

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

┌─────────────┐ ┌──────────────────┐ ┌──────────────┐
│ AI Agent │────▶│ MCP (19 tools) │────▶│ .contentrain/│
│ (decides) │ │ (enforces) │ │ (stores) │
└─────────────┘ └──────────────────┘ └──────┬───────┘
 │
 ┌──────────────────┐ │
 │ Review UI / Git │◀─────────────┘
 │ (human approves)│
 └──────────────────┘

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')

npx skills add Contentrain/ai/packages/skills

npx skills add Contentrain/ai/packages/skills --skill contentrain-normalize

npx contentrain init # initialize project
npx contentrain serve # local review UI (port 3333)
npx contentrain serve --stdio # MCP over stdio for IDE agents
npx contentrain validate # check content health
npx contentrain generate # generate typed SDK client
npx contentrain status # project overview
npx contentrain doctor # setup health check
npx contentrain studio login # authenticate with Studio
npx contentrain studio connect # connect repo to Studio project

pnpm install && pnpm build && pnpm test