Atlas / MCP servers / contentrain / ai

aiBLOCK

Name: ai
Author: contentrain

mcp/contentrain/ai

MCP server by contentrain · ai agents · claude code · content governance · Audited 2026-10-11

Repo-native content governance for AI agents. Extract, review, and deliver UI text, docs, and structured content from Git.

Verdict

BLOCK

Grade

Trust score

51 /100

Exposed tools

104 73r · 25w · 6d

Transport

stdio · streamable-http

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/@contentrain/mcp) [](https://www.npmjs.com/package/contentrain) [](https://www.npmjs.com/package/@contentrain/query) [](https://agentskills.io) [](https://ai.contentrain.io) [](LICENSE)

Website · Docs · Discord · Twitter · LinkedIn

Extract, govern, and ship structured content from your codebase.

Contentrain helps teams turn hardcoded UI text, docs, and structured content into a governed, reviewable content layer. Agents can extract, create, translate, and update content, while Contentrain enforces schema, Git review, and portable file output.

Agent extracts or updates content → Contentrain standardizes → Human reviews → 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, review branches, and a local UI — no account, no cloud, no proprietary content format.

Start here:

What Contentrain is for

Rescuing hardcoded strings from existing apps and turning them into struc

Read from source at commit 680a73720388OBSERVED · 2026-10-11

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)

claude mcp add mcp -- npx -y @contentrain/[email protected]

Exposed tools (104)

73 read · 25 write · 6 destructive. Blast radius: 6 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`.NET`	read	Microsoft .NET platform
`Ada`	read	Writes things.
`Analog`	read	Angular meta-framework
`Angular`	read	Platform for web applications
`Astro`	read	Content-first web framework
`Django`	read	Python web framework
`Electron`	read	Cross-platform desktop apps
`Eleventy`	read	JavaScript static site generator
`Expo`	read	React Native toolchain
`Express`	read	Minimal Node.js web framework
`Fastify`	read	Fast Node.js web framework
`Flutter`	read	Cross-platform UI toolkit (Dart)
`Go`	read	Go programming language
`Hello`	write	A post
`Hugo`	read	Go-based static site generator
`Jekyll`	read	Ruby-based static site generator
`Laravel`	read	PHP web framework
`NestJS`	read	Progressive Node.js framework
`Next.js`	read	React framework with SSR/SSG
`Node.js`	read	Server-side JavaScript runtime
`Nuxt`	read	Vue meta-framework with SSR/SSG
`Other`	read	Unknown or unsupported framework
`Rails`	read	Ruby web framework
`React`	read	UI library for web and native
`Remix`	read	Full-stack React framework
`Rust`	read	Rust programming language
`Solid`	read	Reactive UI library
`Svelte`	read	Compile-time UI framework
`SvelteKit`	read	Svelte meta-framework
`Tauri`	read	Lightweight desktop apps (Rust)
`Vue`	read	Progressive JavaScript framework
`activity`	read	Show recent activity from Studio
`branches`	read	Manage content branches on Studio
`cdn-build`	write	Trigger a CDN rebuild
`cdn-init`	write	Set up CDN for content delivery
`connect`	read	Connect this repository to a Contentrain Studio project
`contentrain`	read	Contentrain CMS architecture, content formats, and MCP tool usage
`contentrain-bulk`	read	Batch operations on content entries
`contentrain-content`	write	Create and manage content entries for existing models
`contentrain-diff`	read	View content diffs between branches
`contentrain-doctor`	read	Diagnose project health issues
`contentrain-generate`	read	Generate the typed SDK client from models
`contentrain-init`	read	Initialize a new Contentrain project
`contentrain-migrate-wordpress`	write	Import a WordPress site into a .contentrain store and wire it to a framework
`contentrain-model`	write	Design and save model definitions
`contentrain-normalize`	write	Two-phase normalize: extract hardcoded strings and patch source files
`contentrain-quality`	read	Content quality, SEO, accessibility, and media rules
`contentrain-review`	read	Review content changes before publishing
`contentrain-sdk`	read	Query SDK usage: #contentrain imports, QueryBuilder, type-safe content access
`contentrain-serve`	write	Start the local review and normalize UI
`contentrain-translate`	read	Translate content across supported locales
`contentrain-validate-fix`	read	Validate content and auto-fix structural issues
`contentrain_apply`	write	Apply normalize operations. Two modes:
`contentrain_branch_delete`	destructive	Delete a pending contentrain (cr/) branch that will not be merged — e.g. a branch left behind by a failed operation, or a superseded draft. Only cr/ branches can be deleted; the contentrain branch is protected. This is destructive: the branch and its unmerged commits are removed.
`contentrain_branch_list`	write	List pending contentrain (cr/*) branches with their merge status against the contentrain branch. Use this to discover branch names for contentrain_merge / contentrain_branch_delete, and to monitor branch-health limits (warning at 50, blocked at 80 unmerged).
`contentrain_bulk`	read	Batch operations on content entries. All operations are auto-committed to git.
`contentrain_content_delete`	destructive	Delete content entries. For dictionaries, use
`contentrain_content_list`	read	List content entries (read-only). Returns data from .contentrain/ — do NOT manually create or modify content files.
`contentrain_content_save`	write	Save content entries. Entry format varies by model kind: DICTIONARY — provide
`contentrain_describe`	write	Get full schema of a single model (read-only). Do NOT manually create content files — use contentrain_content_save instead.
`contentrain_describe_format`	read	Describes the Contentrain content file format for any language/platform. Returns a comprehensive specification of the file structure, JSON formats, markdown conventions, meta files, and locale strategies.
`contentrain_doctor`	read	Project health report (read-only). Returns structured checks: git, node, .contentrain/ structure, model parse, orphan content, branch pressure, SDK freshness. Pass
`contentrain_init`	read	Initialize .contentrain/ structure. Changes are auto-committed to git — do NOT manually create .contentrain/ files.
`contentrain_media_delete`	destructive	Delete a media asset from the media stack. Content entries referencing its path are NOT rewritten — check references before deleting.
`contentrain_media_get`	read	Get a single media asset by id, including its storage path, delivery URL, and metadata.
`contentrain_media_ingest`	read	Ingest a media asset from a source URL. The provider fetches the URL server-side under its own SSRF/MIME/size policy and stores the asset in the media stack. Returns the stored asset with its media/... path.
`contentrain_media_list`	read	List media assets from the provider media stack. Returns storage paths (media/...) usable in media/image/file fields via contentrain_content_save, plus delivery URLs when available. Supports search, tag filter, and cursor pagination.
`contentrain_media_update`	write	Update metadata (alt text, tags, filename) of an existing media asset. Does not touch the binary.
`contentrain_merge`	write	Merge a review-mode branch into contentrain. Local git operation — no external platform needed. Merges the feature branch into the contentrain branch, advances the base branch via update-ref, selectively syncs .contentrain/ files to the working tree, and prunes the merged branch. Target by exact
`contentrain_model_delete`	destructive	Delete a model and its content/meta. Changes are auto-committed to git — do NOT manually edit .contentrain/ files.
`contentrain_model_save`	write	Create or update a model definition. Changes are auto-committed to git — do NOT manually edit .contentrain/ files after calling this tool.
`contentrain_reconcile`	read	Reconcile a diverged contentrain ↔ base-branch pair with a content-aware three-way merge.
`contentrain_scaffold`	read	Template-based project setup. Available templates: ${listTemplates().join(
`contentrain_scan`	read	Scan project source code for content strings. Three modes:
`contentrain_status`	read	Get full project status (read-only). Returns config, models, context. Do NOT manually edit .contentrain/ based on this output.
`contentrain_submit`	write	Push contentrain/* branches to remote. MCP is push-only — PR creation is handled by the platform. Do NOT manually push or create PRs.
`contentrain_validate`	read
`contentrain_vocabulary_delete`	destructive	Remove canonical vocabulary terms by slug. Content already using a term is not touched — the vocabulary only advises. Changes are auto-committed to git.
`contentrain_vocabulary_save`	write	Add or update canonical vocabulary terms. Terms nest as {
`delta`	write	Plan a WordPress source delta against the store (dry run only; applying goes through review)
`describe`	write	Show the schema, stats, and import snippet for a model
`describe-format`	read	Print the Contentrain content-format specification
`diff`	read	Review pending contentrain branches
`doctor`	read	Check project health and environment
`generate`	read	Generate typed SDK client from models
`import`	write	Import a WordPress site (WXR export file or REST URL) into a .contentrain content store
`init`	read	Initialize Contentrain in your project
`login`	read	Authenticate with Contentrain Studio
`logout`	read	Log out from Contentrain Studio
`merge`	write	Merge one contentrain feature branch into the content branch
`prune`	destructive	Delete merged cr/* branches locally and on the remote
`reconcile`	write	Merge a diverged base branch back into the content branch, content-aware
`record_answers`	read	Record the answers for every item.
`scaffold`	write	Apply a Contentrain template (models + sample content + vocabulary)
`serve`	write	Start the local content viewer or the MCP server (stdio for IDE agents, --mcpHttp for Studio / CI / remote drivers)
`setup`	read	Configure MCP server and AI rules for your IDE
`skills`	write	Install, update, or list Contentrain AI skills and rules for your IDE
`status`	read	Show project status overview
`studio`	read	Interact with Contentrain Studio
`submissions`	read	Manage form submissions on Studio
`usage`	read	Show workspace usage metrics
`validate`	read	Validate project content against schemas
`webhooks`	read	Manage webhooks on Studio
`whoami`	read	Show current Studio authentication status

Trust audit

BLOCKgrade F · trust 51/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	WARN
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (5 observation(s))
Network: declared (6 observation(s))
Shell: declared (5 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (25)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/cli/src/commands/serve.ts:179

exec(`${cmd} ${url}`)

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

packages/cli/src/utils/browser.ts:14

exec(command, () => {

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

MEDIUMInventory / provenance · inv.binary · CWE-1104

packages/mcp/src/core/migration/allowlist.ts

allowlist.ts

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

packages/cli/src/studio/auth/oauth-server.ts:55

const callbackUrl = `http://127.0.0.1:${port}/callback`

MEDIUMNetwork egress · net.raw_ip · CWE-200, CWE-319

packages/cli/src/studio/auth/oauth-server.ts:90

const url = new URL(req.url, `http://127.0.0.1:${port}`)