dotCMS MCP SERVER

Where AI Agents Meet Governed Content

The dotCMS MCP server connects AI Assistants directly to a dotCMS instance, allowing you to create full sites, migrate sites and content, and make your pages accessible using natural language instead of the UI.

See how it works Read the docs

A secure bridge between AI and your content infrastructure.

An MCP (Model Context Protocol) server is a secure connector that lets AI tools see and act on a real system the way a person would: what content exists, how it's structured, what it's allowed to touch. For dotCMS, that means an AI agent can search, create, and update content, execute workflow steps, and generate code — all inside the same permissions and audit trail your human team already works under.

“Your next content teammate might not be human — but it must be governed like one.”

— Freddy Montes, VP of Prodcut, dotCMS

One server. Built for two teams.

Marketers and developers both work through the same secure MCP layer —

each with tooling shaped for how they actually work.

For Marketers

Describe what you want, get live pages without a dev ticket
Build sites, pages, and content models by prompt
Search content without writing queries
Surface SEO wins in your existing content
Fix SEO and GEO issues as they're found
Catch off-brand content before it publishes
Works inside your existing workflow

For Developers

Generate code components, forms, and integrations based on your actual dotCMS content structure
Migrate JS to TypeScript automatically
Sync design and content via Figma pairing
Make your site accessible
Go from content model to published page in one instruction
Develop AI assistants that need to understand your content structure

Four steps from zero to agent.

Start prompting

"Show me all my content types" or "Generate a React component for my Product content type."

Configure your AI assistant

Claude Desktop or Cursor are documented today — drop in the config snippet below.

Create an AI User + API token

Scoped to only the permissions the agent needs. Least privilege by default.

Get a dotCMS environment

Cloud, self-hosted, or just use the dotCMS demo site to try it out — no setup required.

>_ claude_desktop_config.json

{
  "mcpServers": {
    "dotcms": {
      "command": "npx",
      "args": ["-y", "@dotcms/mcp-server@beta"],
      "env": {
        "DOTCMS_URL": "https://your-dotcms-instance.com",
        "AUTH_TOKEN": "your-auth-token"
      }
    }
  }
}

Governance built in, not bolted on.

The same enterprise controls dotCMS customers already rely on — extended to every AI action the moment it happens.

See our Security & Compliance

Every AI action is logged, traceable, and reversible

Role-based permissions decide exactly what each agent can see or edit

API tokens are sandbox-isolated and never exposed to the AI model itself

Built on the open Model Context Protocol standard — no proprietary lock-in

Questions, answered.

Still curious? The docs go deep on setup, permissions, and every tool the server exposes.

Read the docs

It's a secure connector implementing the open Model Context Protocol. It lets AI assistants read your dotCMS content, schemas, and workflows — and take governed actions like creating content, executing workflow steps, or generating code — through scoped API tokens.

Evergreen is recommended. Version 24.4 is the minimum supported release.

Claude Desktop and Cursor are documented today. Because MCP is an open standard, any MCP-compatible client can connect.

No — the public demo site at demo.dotcms.com works. Point the server at it, generate a token, and try prompts without provisioning anything.

No. Tokens are sandboxed on the MCP server side and never included in prompts or responses sent to the model.

Content Types, Content, and Workflows — scoped to whatever the agent should actually do. We strongly recommend least privilege: grant read where possible, and only add write on the specific types the agent needs.

Ask it anything you'd otherwise do by clicking through the dotCMS back end or writing a REST script — find and bulk-edit content, push things through workflow, build or refactor content types, and build front end components, themes, and templates.

AI in CMS

18 Aug 26
AI You Can Actually Turn On: A 7-Control Governance Framework
A breakdown of how AI is architected and governed in dotCMS. A seven-control framework for turning on AI without losing governance — model choice, data boundaries, and permission-bound agents, explained.
3 Aug 26
Bring your own AI model to dotAI
Bring your own AI model to dotAI in dotCMS. Choose from Azure OpenAI, AWS Bedrock, Google Vertex AI, OpenAI, Anthropic, Gemini, or OpenRouter to run writing assistance, workflows, auto-tagging, semantic search, and image generation within your approved cloud and governance rules.
24 Apr 26
From AI assisted to Agent-ready: How dotCMS is Building for the Agentic-age
Agentic AI is changing what enterprise content platforms need to do. The next CMS battle is not about AI features. It is about whether autonomous agents can safely create, govern, translate, and publish content through stable APIs, workflows, and audit trails. dotCMS is built for that shift.
21 Mar 26
Structured Content for GEO: How dotCMS Powers AI-Ready Digital Experiences
Discover how dotCMS revolutionizes AI-driven digital experiences with structured content for Generative Engine Optimization (GEO). Learn how our enterprise solution enhances AI visibility, enabling large language models to accurately process and cite machine-readable data. Dive into best practices for creating AI-ready content and explore the benefits of a headless CMS model. Optimize your content for AI discovery and experience seamless omnichannel delivery. Contact us to leverage dotCMS for your AI-powered search needs.
9 Mar 26
AI Governance for Enterprise Content Operations
Learn why AI content governance is essential for content teams. Discover how to protect brand consistency, reduce legal risk, and manage AI across dozens of sites with dotCMS’s built-in governance tools.