Back to MCP Servers

Lightcms

AI-native CMS with 72 MCP tools for managing websites through natural language. Create and publish content, manage templates, assets, snippets, themes, collections, redirects, and multi-site forks — with full content versioning and semantic search.

developer-toolsai
By jonradoff
192Updated 3 months agoGoMIT

Installation

npx -y lightcms

Configuration

{
  "mcpServers": {
    "lightcms": {
      "command": "npx",
      "args": ["-y", "lightcms"]
    }
  }
}

How to use

  1. Run the installation command above (if needed)
  2. Open your Claude Code settings file (~/.claude/settings.json)
  3. Add the configuration to the mcpServers section
  4. Restart Claude Code to apply changes

README

View on GitHub

LightCMS

CI codecov Go Report Card lightcms MCP server

LightCMS is a Go-powered content management system built for the AI era. It's simultaneously AI-native (semantic search, built-in Claude-powered chat widget, MCP server for agent control), agentically controllable (Claude Code and any MCP client can read, write, publish, and bulk-import content via 106 MCP tools), and agentically updatable (the codebase is clean, well-structured Go — coding agents can safely extend it). For teams that want a CMS that works with AI rather than around it.

What's New in v6.0

FeatureSummary
Content ApprovalsContributors submit content for approval; editors/admins approve or reject from /cm/approvals. Rejection comments auto-post to the discussion thread.
Contributor RoleNew RBAC role between Viewer and Editor. Can create content + upload assets (pending), post comments, and submit for approval — but cannot publish directly or manage system settings.
Approval WorkflowsConfigurable trigger-based workflows (contributor, folder path, template ID, or tag). Sequential or concurrent mode with configurable approver lists.
Content DiscussionInline comment thread at the bottom of every edit page. @mention autocomplete, live badge count, admin delete.
Tabbed Bottom PanelDiscussion, Version History, and Forks organized into tabs on the content edit page.
Approvals DashboardMy Queue + Other Pending + Workflow Config at /cm/approvals. Sidebar badge shows pending count.
Dashboard SectionsRequiring Approvals and Recent Comments appear on the admin dashboard when relevant.
New Webhook Eventscomment.created, content.pending_approval, asset.pending_review.
14 new MCP toolsFull comment and approval lifecycle — list/create/delete comments, full workflow CRUD, list/get/submit/approve/reject/cancel approval requests.

What's New in v5.0

FeatureSummary
Import PipelineThree new import types — RSS/Atom feeds, Markdown/ZIP upload, CSV bulk import — with a unified job dashboard at /cm/imports.
RSS/Atom ImportConfigure recurring feed sources with hourly/daily/weekly schedules, template mapping, folder targeting, and auto-publish.
Markdown ImportUpload .md files or .zip archives with YAML frontmatter. Supports Notion exports, Obsidian vaults, Hugo/Jekyll migrations, and AI-generated content.
CSV ImportUpload CSV files and map columns to content fields. Specify the title column; all other columns become fields automatically.
Real-time Job StatusSSE-powered live log stream at /cm/imports/{jobID}. Watch imports happen line-by-line or review full history after the fact.
10 new MCP import toolslist_import_sources, create_import_source, update_import_source, delete_import_source, trigger_import_source, import_markdown, import_csv, list_import_jobs, get_import_job, cancel_import_job.
Agentic bulk content creationimport_markdown is designed for AI agents to generate and import large content batches in a single call. See MCP.md.
DeduplicationImports match by full_path — re-importing the same slug updates rather than duplicates.

What's New in v4.5

FeatureSummary
WebhooksHMAC-SHA256 signed events for publish, unpublish, delete, create, update. Admin UI at /cm/webhooks with delivery history and a docs page.
Scheduled PublishingSet a future publish_at timestamp on any content item; a background scheduler auto-publishes at the right time.
Content LockingAdvisory lock when editing (30-min expiry). Warning banner if another user is already editing. Admins can force-unlock.
Incremental Static Regeneration (ISR)Template layout changes regenerate affected pages in 20-page batches, preventing server overload on large sites.
Edge Caching HeadersETag, Cache-Control, Last-Modified, and Vary headers on all public pages. 304 Not Modified support.
Cloudflare IntegrationConfigure Zone ID + API Token to auto-purge Cloudflare cache on publish/unpublish.
Structured JSON LoggingAll server logs emit structured JSON with timestamp, level, message, and context fields.
Rate Limit DashboardNew tab on the audit log page showing locked IPs, attempt counts, and a one-click clear button.
MCP Prompt ResourcesThree new MCP resources: lightcms://site/structure, lightcms://content/recent, lightcms://theme/config.

Why LightCMS?

Lightweight: A clean, focused codebase that's easy to understand, modify, and extend. No bloated frameworks or complex abstractions.

AI-Native: Built from the ground up for the AI era:

  • MCP Integration: Full Model Context Protocol server with 106 tools and 3 prompt resources for website management. Supports both local stdio and HTTP streamable transports — connect from Claude Code, Claude Desktop, or any MCP-compatible client.
  • OAuth 2.1 for Remote Agents: Sandboxed desktop apps like Claude's Cowork can securely connect over HTTP using OAuth 2.1 with PKCE. No embedded passwords — just authorize once and the agent manages your site.
  • Fork-Friendly: Designed to be forked and customized by Claude Code. Ask Claude to add new content types, modify templates, or build custom features — the codebase is structured for AI-assisted development.
  • Natural Language Website Management: Skip the admin UI entirely. Create pages, manage assets, customize themes, and publish content through conversation.

Features

Content Management

  • Template System: Define reusable content structures with custom fields (text, richtext, image, date, select, markdown)
  • Static Page Generation: Fast page loads from pre-rendered HTML — no runtime templating overhead
  • Content Versioning: Full version history with diff comparison and one-click revert
  • Soft Delete: Recover deleted content with undelete functionality
  • Content Tagging: Tag any content item with one or more freeform labels, then query by tag across your site
  • Snippets: Named HTML template fragments used as reusable rendering units in dynamic queries
  • lc:query Directives: Embed live content queries directly in template layouts — at publish time they expand into rendered lists of matching pages
  • Content Collections: Auto-generated paginated listing pages filtered by category
  • Folders & URL Organization: Hierarchical content organization with clean URL paths
  • Rich Text Editor: TinyMCE integration for visual content editing
  • Regex Search & Replace: Site-wide or scoped search-and-replace with RE2 regex support, capture groups, and mandatory preview step
  • Bulk Operations: Update or apply field operations across up to 100 pages in a single API call; export/transform/re-import pipelines
  • Scheduled Publishing (v4.5+): Set a future publish_at timestamp; a background scheduler auto-publishes at the right time
  • Content Locking (v4.5+): Advisory lock while editing (30-min expiry); warning banner if another user holds the lock; admins can force-unlock
  • Incremental Static Regeneration (v4.5+): Template layout changes regenerate pages in 20-page batches to prevent server overload on large sites

Import Pipeline (v5.0+)

  • RSS/Atom Feed Sources: Configure recurring import sources with configurable schedule (hourly/daily/weekly), template mapping, folder targeting, and auto-publish. Manage sources and run history from /cm/imports.
  • Markdown + ZIP Import: Upload .md files or .zip archives of Markdown. YAML frontmatter in each file controls title, slug, folder, template, tags, and scheduled publish time. Supports Notion exports, Obsidian vaults, Hugo/Jekyll site migrations, and AI-generated content.
  • CSV Bulk Import: Upload a CSV and specify which column is the title; all other columns are stored as content fields automatically.
  • Real-time SSE Job Status: Live log stream at /cm/imports/{jobID} — watch imports happen line-by-line or review full history after the fact.
  • MCP-first Design: import_markdown is specifically designed for AI agents to generate and import large content batches in a single call, replacing dozens of create_content calls with one import_markdown + one get_import_job. See MCP.md for workflow examples.

Content Forks (v4.0+)

  • Fork Workspaces: Create named staging workspaces where sets of page edits can be authored, previewed, and reviewed before going live
  • Sparse Model: Only edited pages live in a fork — unmodified pages fall through to live content automatically
  • Fork Preview Mode: Activate via a floating bar injected into the live site; a cookie routes all page requests through the fork so you see exactly how the site will look after merge
  • Merge with Conflict Detection: Admins merge forks into live content; if a live page was changed after the fork was created, the conflict is recorded (fork wins). New pages created in the fork are inserted into live on merge
  • Full MCP Toolset: 8 dedicated fork tools — list_forks, create_fork, get_fork, fork_page, remove_fork_page, merge_fork, archive_fork, delete_fork

Batch & Parallel Operations

Designed for agents that prefer parallelized, high-throughput workflows over sequential single-item calls:

  • bulk_update_content: Update up to 100 pages in a single API call. Each item uses merge semantics — only the fields you specify are touched. Supports dry_run validation before committing, and auto_republish to re-publish all previously-published pages in the same call, eliminating a separate publish step
  • bulk_field_operation: Apply a single operation (set, clear, prepend, append, wrap) to a field across every matching page in one call. Scope by template, folder, category, or explicit ID list. Ideal for adding disclaimers, updating metadata, or clearing stale fields across a content type
  • publish_multiple: Publish a list of IDs — or all drafts at once with publish_all_drafts: true — in a single request instead of looping over publish_content
  • export_content: Dump full field data for a scoped set of pages as a structured JSON array. Designed for export → transform → re-import pipelines; pair with bulk_update_content for large-scale content migrations
  • Scoped Search & Replace: Both scoped_search_replace_preview and scoped_search_replace_execute accept scope filters (folder, template, category, IDs) so agents can target precise subsets rather than running site-wide operations
  • Parallel-Safe Read API: list_content with include_data: true returns full field values in one fetch; agents can fan out reads across multiple list_content / get_content calls concurrently and then batch-write with bulk_update_content

Recommended agent pattern for large updates: list_content → transform in parallel → bulk_update_content (up to 50/call) → publish_multiple.

AI Chat Widget (v4.2+)

  • Embeddable Widget: Add a floating AI chat bubble to any page with a single <script> tag — self-contained, no build step required
  • Two-Phase Pipeline: Each visitor query runs hybrid semantic+fulltext search to retrieve relevant content

…

View source on GitHub

You might also like

Checkyourself
MCP Servers
Mason
MCP Servers
Selvedge
MCP Servers