Skip to main content
Glama

Directus MCP Server

Warning

This was an experimental MCP server to test the waters and see what it would allow us to do. We've since released an official Directus MCP server over on https://github.com/directus/mcp 🙂


Directus Model Context Protocol (MCP) Server

MCP server for use with Directus. Allows your AI tools to connect to and use your Directus API on your behalf.

This is an experiment by yours truly (@rijkvanzanten). Any and all PRs are more than welcome :)

Installation

This MCP server is built to work with NodeJS v22.12 or newer.

npm install -g @rijk/directus-mcp-server

Then configure Claude AI to use the npm package as remote server:

{ "mcpServers": { "directus": { "command": "directus-mcp-server", "env": { "DIRECTUS_URL": "<your Directus instance URL>", "DIRECTUS_TOKEN": "<your Directus user token>" } } } }

Local / Dev Installation

  1. Clone the repo
  2. pnpm install && pnpm build to build the server
  3. Configure Claude AI like above, but pointing it to the dist file instead:
{ "mcpServers": { "directus": { "command": "node", "args": ["/path/to/directus-mcp-server/dist/index.js"] } } }

Tools

Read Items

The read-items tool allows you to read items from any Directus collection by providing the collection name as a parameter.

Parameters:

  • collection: (required) The name of the collection to read from
  • fields: (optional) Array of field names to return
  • sort: (optional) Field to sort by (prefix with - for descending order)
  • limit: (optional) Maximum number of items to return

Example:

{ "collection": "articles", "fields": ["id", "title", "date_published"], "sort": "-date_published", "limit": 10 }

Read Current User

Get information about the current user. Effectively the /users/me endpoint.

Read Collections

Return what collections/fields are available in the system. Use this tool first to discover available collections before using the read-items tool.

License

MIT

-
security - not tested
A
license - permissive license
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A Model Context Protocol server that allows AI tools to connect to and interact with your Directus API, enabling automated access to collections, items, and user data.

  1. Installation
    1. Global Installation (Recommended)
    2. Local / Dev Installation
  2. Tools
    1. Read Items
    2. Read Current User
    3. Read Collections
  3. License

    Related MCP Servers

    • A
      security
      F
      license
      A
      quality
      A Node.js server that enables AI Clients to interact with the Directus CMS API through the Model Context Protocol, allowing for management of collections, items, files, users, and system information.
      Last updated -
      18
      15
      TypeScript
    • -
      security
      A
      license
      -
      quality
      A server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.
      Last updated -
      2
      8
      TypeScript
      MIT License
    • -
      security
      F
      license
      -
      quality
      A Model Context Protocol server that provides AI models with structured access to external data and services, acting as a bridge between AI assistants and applications, databases, and APIs in a standardized, secure way.
      Last updated -
      1
      Python
    • -
      security
      A
      license
      -
      quality
      An extension that implements the Model Context Protocol for Directus, enabling AI tools and LLMs to interact with Directus content through natural language for content editing, data analysis, and asset management.
      Last updated -
      4
      6
      TypeScript
      MIT License

    View all related MCP servers

    MCP directory API

    We provide all the information about MCP servers via our MCP API.

    curl -X GET 'https://glama.ai/api/mcp/v1/servers/rijkvanzanten/directus-mcp-server'

    If you have feedback or need assistance with the MCP directory API, please join our Discord server