4,500+ servers built on MCP Fusion
Vinkius
Directus logo
Vinkius
Claude Code logo

How to Use the Directus MCP in Claude Code

Run headless database migrations, schema audits, and user checks from Claude Code in your terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Directus MCP on Cursor AI Code Editor MCP Client Directus MCP on Claude Desktop App MCP Integration Directus MCP on OpenAI Agents SDK MCP Compatible Directus MCP on Visual Studio Code MCP Extension Client Directus MCP on GitHub Copilot AI Agent MCP Integration Directus MCP on Google Gemini AI MCP Integration Directus MCP on Lovable AI Development MCP Client Directus MCP on Mistral AI Agents MCP Compatible Directus MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Directus MCP to Claude Code

Create your Vinkius account to connect Directus to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Scriptable database audits from the terminal

Running `list_schema_collections` lets Claude Code audit PostgreSQL configurations directly from your terminal session. The agent calls `get_collection_details` to dump database structures into your shell. Running `list_collection_fields` via this MCP Server eliminates the need for heavy GUI clients when checking column types. You can pipe the agent's output into standard Unix utilities, allowing you to quickly compare environments.

Automate CI/CD pipelines with Claude Code

Calling `list_directus_users` lets Claude Code check for active admin accounts before running database migrations. It ensures your staging and production environments match without manual web checks. Running `list_directus_files` lets the agent verify media storage assets during your automated CI/CD pipeline runs. It can also seed rows with `create_cms_record` and clean up using `wipe_cms_record` once the pipeline completes.

Fast data patches and row inspection

Using `get_single_item` lets Claude Code fetch explicit database rows by UUID to inspect columns during an incident. You don't need to write complex SQL queries under pressure. Running `patch_cms_record` lets the agent apply database fixes directly from your command line. It modifies the target database value in seconds, reducing mean time to resolution during outages.

Setup guide

Set up Directus MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see directus-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Directus transactions." It will automatically discover and invoke the available Directus tools.

Terminal
claude mcp add --transport http directus-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Directus MCP in Claude Code

Run `claude mcp add` in your terminal, specifying the HTTP transport and your Vinkius endpoint URL. The CLI will update your local configuration file and immediately load the database tools.
Yes. You can instruct the CLI tool to find matching rows using `list_collection_items` and then loop through them to apply updates using `patch_cms_record` directly from your terminal session.
Absolutely. Because Claude Code runs entirely in the terminal, this MCP Server works perfectly over SSH connections, inside Docker containers, and within your automated GitHub Actions pipelines.
Run `claude mcp list` in your shell. The command will display the active connection status and show all ten database tools, including `wipe_cms_record` and `list_collection_fields`.
Your database rows, PostgreSQL table schemas, and admin user profiles are protected by Vinkius's zero-trust V8 Isolate Sandbox. No database credentials or raw payloads are cached, ensuring secure terminal operations.

Start using the Directus MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Directus. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.