Join us for a Live Demo & Q&A Session
AI

Overview

Connect AI assistants directly to your Directus instance. Let Claude, ChatGPT, and other AI tools read and write your content without manual copy-pasting.

AI assistants can now directly access your Directus content using the Model Context Protocol (MCP). Instead of copying data back and forth, your AI tools connect directly to your Directus instance.

MCP is currently in Beta and requires Directus v11.12 +. For older versions, use the Local MCP alternative.

Is this for you?

  • Content editors: Migrate content from Google Docs, organize individual files, and manage content with AI assistance.
  • Developers: Rapidly prototype data models, create collections, and build automation workflows.
  • Teams: Dramatically speed up content operations while maintaining brand consistency.

Get started with the Directus MCP Server

Quick Setup

Enable MCP and connect your AI tools in under 5 minutes.

See What's Possible

Real examples of AI-powered content workflows that save hours of manual work.

Available Tools

Complete reference of MCP tools and their capabilities.

Custom Prompts

Create reusable prompt templates for consistent AI interactions.

Security Guide

Essential security practices for using MCP safely with your Directus data.

Troubleshooting

Common issues and solutions when setting up and using the Directus MCP server.

Local Alternative

Node.js-based MCP server for advanced setups and older Directus versions.

What you can do with the Directus MCP Server?

For Content Editors

Use LLMs and AI to create and manage content.

  • Import blog posts from Google Docs with proper field mapping
  • Build landing pages using page builder components and relationships
  • Add metadata to individual images (alt text, descriptions, tags)
  • Organize files into logical folder structures
  • Create content entries with proper relationships to authors, categories, etc.

For Developers

Rapidly prototype data models and build automation using natural language.

  • Create collections with proper field types and validation rules
  • Set up complex relationships (M2O, O2M, M2M, M2A) between collections
  • Generate automation flows triggered by database events
  • Build approval workflows with custom operations
  • Prototype entire data models through conversation

How it works

  1. Enable MCP in Directus Settings → AI
  2. Create access token for your MCP user (we recommend creating a dedicated user for MCP operations)
  3. Connect your AI tool to the Directus MCP server
  4. Use AI to create, edit, and manage your content

Your AI assistant operates through your existing Directus permissions - no middleware or data copying required.

Security built-in

  • Uses your existing Directus permissions
  • Complete audit trail of all changes
  • Global delete protection (disabled by default)
Security: For production deployments, review our comprehensive Security Guide covering threat mitigation, compliance requirements, and enterprise security controls.

Supported clients

Real-world examples

Content Creation

I have this blog post in Google Docs about AI trends in 2024. Can you import it as a new article in my blog collection?
I'll help you import that article. Let me first check your blog collection structure to understand the available fields... I can see you have fields for title, content, author, category, tags, and published_date. Please share the Google Doc content and I'll create a properly formatted blog post entry with the correct relationships.
shares Google Doc content
Perfect! I've created a new blog post with:
  • ✅ Title: "AI Trends Shaping 2024: A Comprehensive Overview"
  • ✅ Content: Properly formatted with headings and paragraphs
  • ✅ Author: Linked to your user profile
  • ✅ Category: Set to "Technology"
  • ✅ Tags: Added "AI", "trends", "2024", "technology"
  • ✅ Status: Set to "draft" for your review
The article is now available at: /admin/content/blog/123Would you like me to make any adjustments or set it to published status?
Behind the scenes: The AI uses the schema tool to understand your collection structure, then the items tool to create the entry with proper field mapping and relationships.

Asset Organization

I have this blog post in Google Docs about AI trends in 2024. Can you import it as a new article in my blog collection?
I'll help you import that article. Let me first check your blog collection structure to understand the available fields... I can see you have fields for title, content, author, category, tags, and published_date. Please share the Google Doc content and I'll create a properly formatted blog post entry with the correct relationships.
Behind the scenes: The AI uses the assets tool to analyze the image content, then the files tool to update metadata and the folders tool for organization.

Data Modeling

I have this blog post in Google Docs about AI trends in 2024. Can you import it as a new article in my blog collection?
I'll help you import that article. Let me first check your blog collection structure to understand the available fields... I can see you have fields for title, content, author, category, tags, and published_date. Please share the Google Doc content and I'll create a properly formatted blog post entry with the correct relationships.
shares Google Doc content
Perfect! I've created a new blog post with:
  • ✅ Title: "AI Trends Shaping 2024: A Comprehensive Overview"
  • ✅ Content: Properly formatted with headings and paragraphs
  • ✅ Author: Linked to your user profile
  • ✅ Category: Set to "Technology"
  • ✅ Tags: Added "AI", "trends", "2024", "technology"
  • ✅ Status: Set to "draft" for your review
The article is now available at: /admin/content/blog/123Would you like me to make any adjustments or set it to published status?
Behind the scenes: The AI uses the collections, fields, and relations tools to create a complete data model with proper Many-to-One and Many-to-Many relationships.

Get once-a-month release notes & real‑world code tips...no fluff. 🐰