[!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.
Global Installation (Recommended)
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
- Clone the repo
pnpm install && pnpm buildto build the server- Configure Claude AI like above, but pointing it to the
distfile 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 fromfields: (optional) Array of field names to returnsort: (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
Recommend MCP Servers 💡
redis/mcp-redis
A natural language interface for AI agents to efficiently manage and search data in Redis, supporting various Redis data structures and integrating seamlessly with MCP clients.
kafka-mcp
A MCP Server for Kafka that enables AI-driven workflows to manage Kafka operations such as producing/consuming messages, managing topics, brokers, partitions, and offsets.
chroma-mcp
A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma
Jite-J/-mysql_mcp_server
An MCP implementation for secure interaction with MySQL databases, enabling AI applications to explore and analyze data safely and in a structured manner.
fastomop/omcp_a2a
An MCP server providing tools for interacting with OMOP CDM databases and generating SQL queries using NLP, integrated with Ollama.
achrekarom12/mcp-mongo
A Model Context Protocol (MCP) server enabling large language models (LLMs) to communicate directly with MongoDB, supporting natural language database queries, schema exploration, and data operations.