Name: Contentrain MCP
Author: Contentrain

LABSCO SUMMARY

Every write is a git transaction on a throwaway worktree — your working tree is never touched.

A dedicated contentrain branch holds content state, each write forks a cr/ branch in a temporary worktree, and the result merges back with canonical JSON formatting. Nothing stashes or checks out under you while you work. The tool list is also capability-aware: a session driven by a remote provider with no local checkout only advertises the tools it can actually satisfy, rather than failing halfway through one.

What it is

The engine behind Contentrain's MCP integration. It manages a .contentrain/ directory in your project — models, content, locales — and every write goes through a git transaction rather than straight onto disk.

What you get

Project status, a model's full schema with sample data, and the file-format contract itself — contentrain_status, contentrain_describe, contentrain_describe_format
A project initialized from scratch or from a starter template — blog, landing, docs, ecommerce, saas, i18n, mobile — contentrain_init, contentrain_scaffold
Models created, updated and deleted, with content and meta files following — contentrain_model_save, contentrain_model_delete
Content entries saved, listed with filters and locales resolved, and deleted down to individual dictionary keys — contentrain_content_save, contentrain_content_list, contentrain_content_delete
Validation against the model schemas — required fields, type mismatches, broken relations, secret leaks, i18n parity — with structural problems auto-fixed on request — contentrain_validate
Source code scanned for hard-coded strings, then those strings extracted into content files or the source patched to reference them, with a dry run by default — contentrain_scan, contentrain_apply
Batch operations across entries, including locale-to-locale work — contentrain_bulk
Review flow in git: branches pushed for review, merged back into the contentrain branch locally, listed with their merge status, and deleted when abandoned — contentrain_submit, contentrain_merge, contentrain_branch_list, contentrain_branch_delete
A health report covering git, node, structure, model parsing, orphaned content, branch pressure and SDK freshness — contentrain_doctor

Requirements

Node.js 22 or newer and git on the machine; install @contentrain/mcp and run contentrain-mcp over stdio, with CONTENTRAIN_PROJECT_ROOT pointing at the project if it is not the working directory. It is local-first, with optional GitHub and GitLab backends and an HTTP transport for remote drivers such as Contentrain Studio. Optional parsers — @vue/compiler-sfc, @astrojs/compiler and svelte — sharpen source scanning for those frameworks; the scanner works without them.

Setup effort

One command — pnpm add @contentrain/mcp

See installation options

USE CASES

01

Setting up structured content in a project that has none

Scaffold from the template closest to the site, then read back the models it created before writing any content.

contentrain_scaffoldcontentrain_status

02

Getting hard-coded strings out of the source

Scan for candidate strings, review the dry-run preview, then extract them into content files or patch the source to reference them.

contentrain_scancontentrain_apply

03

Adding a content type and filling it

Save the model definition, then save entries against it — both land as commits, not as edits to your working tree.

contentrain_model_savecontentrain_content_save

04

Finding out what is broken before a build does

Validate against the schemas and let it auto-fix the structural problems it can.

contentrain_validatecontentrain_doctor

05

Getting agent-made changes past a human

Push the pending branches for review, then merge the one that was approved into the content branch.

contentrain_submitcontentrain_branch_listcontentrain_merge

06

Clearing branches left behind by an abandoned change

List the pending ones with their merge status and delete the ones that will never land.

contentrain_branch_listcontentrain_branch_delete

19 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`contentrain_apply`

Apply normalize operations. Two modes: "extract" writes agent-approved strings to Contentrain content files (source untouched), "reuse" patches source files with agent-provided replacement expressions. DRY RUN (default, dry_run:true): validates inputs, resolves conflicts, and returns a full preview — NO changes to disk or git. EXECUTE (dry_run:false): writes files to disk, commits to a branch, and requires branch health check to pass. Recommended workflow: always run dry_run first, review the preview, then call again with dry_run:false to execute. Normalize operations always use review workflow (never auto-merge).

BEFORE YOU INSTALL

What to know first

Tools you get

19 tools when we connected; the project documents 25. Tools depend on the provider: local stdio lists 22 core tools, remote GitHub/GitLab providers only 9, and the five contentrain_media_* tools appear only where the provider supports media. contentrain_scan and contentrain_apply need a local provider.

Requires

npx on PATH
Node.js 22+

INSTALLATION

Connect your client

Server setup

TERMINAL

pnpm add @contentrain/mcp

MCP Clients

Claude Code

CLAUDE CODE · TERMINAL

npx contentrain setup claude-code

Cursor

CURSOR · TERMINAL

npx contentrain setup cursor

VS Code

VS CODE · TERMINAL

npx contentrain setup vscode

Windsurf

WINDSURF · TERMINAL

npx contentrain setup windsurf

GitHub Copilot

GITHUB COPILOT · TERMINAL

npx contentrain setup copilot

Any MCP client — stdio

ANY MCP CLIENT — STDIO · TERMINAL

CONTENTRAIN_PROJECT_ROOT=<YOUR_CONTENTRAIN_PROJECT_ROOT> npx contentrain-mcp

Embed in your own process

EMBED IN YOUR OWN PROCESS

import { createServer } from '@contentrain/mcp/server'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'

const server = createServer(process.cwd())
const transport = new StdioServerTransport()

await server.connect(transport)

Contentrain MCP

Every write is a git transaction on a throwaway worktree — your working tree is never touched.

What it is

What you get

Requirements

Setup effort

Setting up structured content in a project that has none

Getting hard-coded strings out of the source

Adding a content type and filling it

Finding out what is broken before a build does

Getting agent-made changes past a human

Clearing branches left behind by an abandoned change

19 tools

contentrain_apply

contentrain_branch_delete

contentrain_branch_list

contentrain_bulk

contentrain_content_delete

contentrain_content_list

contentrain_content_save

contentrain_describe

contentrain_describe_format

contentrain_doctor

contentrain_init

contentrain_merge

contentrain_model_delete

contentrain_model_save

contentrain_scaffold

contentrain_scan

contentrain_status

contentrain_submit

contentrain_validate

What to know first

Tools you get

Requires

Connect your client

Server setup

MCP Clients

Claude Code

Cursor

VS Code

Windsurf

GitHub Copilot

Any MCP client — stdio

Embed in your own process

Same category

Claudeus WordPress MCP

WordPress REST Endpoint MCP Server

Contentful

Strapi MCP

`contentrain_apply`

`contentrain_branch_delete`

`contentrain_branch_list`

`contentrain_bulk`

`contentrain_content_delete`

`contentrain_content_list`

`contentrain_content_save`

`contentrain_describe`

`contentrain_describe_format`

`contentrain_doctor`

`contentrain_init`

`contentrain_merge`

`contentrain_model_delete`

`contentrain_model_save`

`contentrain_scaffold`

`contentrain_scan`

`contentrain_status`

`contentrain_submit`

`contentrain_validate`