Directus

You set up this MCP Server to bridge Directus with a programmable interface, enabling authentication, collections, files, flows, users, schema analysis, and diagnostics through a consistent MCP client workflow.

How to use

Connect your MCP client to the Directus MCP Server using the stdio configuration shown below. You will run the server locally and point your client at your Directus instance with a static API token. Once connected, you can list collections, inspect schemas, manage items, trigger flows, handle files, and perform diagnostics from your assistant-driven commands.

How to install

Prerequisites: you need Node.js installed on your system. You also need npm for package management.

Install the MCP server globally with npm.

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

If you prefer to build from source, clone the project, install dependencies, and build.

git clone https://github.com/staminna/mcp-server-claude.git
cd mcp-server-claude
npm install
npm run build

Configuration and usage notes

To run the MCP server with your Directus instance, you’ll provide the Directus URL and a static API token via environment variables. You can configure your development environment with a stdio-based MCP command that uses npx to start the server.

Troubleshooting

If you cannot connect, ensure Directus is reachable at the URL you supplied and that the API token has the necessary permissions. Restart your IDE or editor after changing MCP settings, and check the console for MCP-related errors.

Development

During development you can build and run the server in watch or dev mode, then start the server when ready.

Notes

The server supports a complete environment-variable configuration set. When running locally, provide the Directus URL and token, and you can also enable optional features such as AI prompts and resources through additional environment variables.

Available tools

list_collections

List all collections in Directus

get_collection_schema

Get schema for a specific collection

get_collection_items

Get items from a collection with filtering

create_collection

Create a new collection

create_item

Create a new item in a collection

update_item

Update an existing item

delete_items

Delete items from a collection

bulk_operations

Execute bulk create, update, delete

create_field

Create a new field in a collection

update_field

Update an existing field

delete_field

Delete a field from a collection

create_relationship

Create relationships between collections

analyze_collection_schema

Analyze schema with relationship mapping

validate_collection_schema

Validate schema and relationships

analyze_relationships

Analyze relationships across collections

get_flows

Get all flows with optional filtering

get_flow

Get a specific flow by ID

create_flow

Create a new automation flow

update_flow

Update an existing flow

delete_flow

Delete a flow

trigger_flow

Manually trigger a flow

get_operations

Get flow operations

get_users

Get all users with filtering

get_user

Get a specific user by ID

get_files

Get files with filtering and pagination

diagnose_collection_access

Diagnose collection access issues

refresh_collection_cache

Refresh collection cache

validate_collection_creation

Validate newly created collections