Directus Task MCP Server

Manage tasks in Directus with automatic schema synchronization.

A Model Context Protocol (MCP) server for managing tasks in Directus with automatic schema synchronization. This server allows you to interact with your Directus PostgreSQL database through AI assistants like Claude or Cursor.

- Task Management: Create, read, update, and delete tasks
- Schema Management: Automatically sync TypeScript models to Directus collections
- Filtering: Filter tasks by status, priority, and other criteria
- Validation: Built-in validation using Zod schemas
- Type Safety: Full TypeScript support with proper typing

- Node.js 18+
- A Directus instance (local or hosted)
- Directus API token or user credentials

The server uses the following environment variables:

- DIRECTUS_URL: Your Directus instance URL (default:https://te9-pg-api.up.railway.app/)
- DIRECTUS_TOKEN: Your Directus API token (default: mo7tahjWjKgHW-42_tEMThJiqBstu2V_)
- DIRECTUS_USER_EMAIL: Alternative to token - user email
- DIRECTUS_USER_PASSWORD: Alternative to token - user password
- Create a.cursor/mcp.jsonfile in your project root:

{ "mcpServers": { "directus-tasks": { "command": "node", "args": ["dist/index.js"], "env": { "DIRECTUS_URL": "https://te9-pg-api.up.railway.app/", "DIRECTUS_TOKEN": "mo7tahjWjKgHW-42_tEMThJiqBstu2V_" } } } }

- Open Claude Desktop settings
- Navigate to Developer tab and click "Edit Config"
- Add the following configuration:

{ "mcpServers": { "directus-tasks": { "command": "node", "args": ["/absolute/path/to/your/project/dist/index.js"], "env": { "DIRECTUS_URL": "https://te9-pg-api.up.railway.app/", "DIRECTUS_TOKEN": "mo7tahjWjKgHW-42_tEMThJiqBstu2V_" } } } }

Important: Replace/absolute/path/to/your/projectwith the actual absolute path to your project directory.

The MCP server provides the following tools:

- sync-task-schema: Synchronizes the Task model schema with your Directus database

- list-tasks: List all tasks with optional filtering by status, priority, and limit
- get-task: Get a specific task by ID
- create-task: Create a new task
- update-task: Update an existing task
- delete-task: Delete a task

- get-user-info: Get current user information

The Task model includes the following fields:

interface Task { id?: string; // UUID primary key title: string; // Required task title description?: string; // Optional description status: 'todo' | 'in_progress' | 'completed'; // Task status priority: 'low' | 'medium' | 'high'; // Task priority due_date?: string; // Optional due date (ISO format) created_at?: string; // Auto-generated creation timestamp updated_at?: string; // Auto-generated update timestamp user_created?: string; // Auto-generated user who created user_updated?: string; // Auto-generated user who updated }

Please sync the task schema with the database

Create a new task with title "Implement user authentication" and high priority

Show me all tasks with status "in_progress"

Update task with ID [task-id] to completed status

src/ ├── models/ │ └── Task.ts # Task model with TypeScript interfaces and Zod schemas ├── services/ │ └── SchemaManager.ts # Schema management service └── index.ts # Main MCP server implementation

- Create a new model file insrc/models/
- Define TypeScript interfaces and Zod schemas
- Export field definitions for Directus
- Add tools to the main server for the new model
- Use SchemaManager to sync the schema

# Install dependencies npm install # Build the project npm run build # Development mode (watch for changes) npm run dev # Start the server directly npm start

- Authentication Errors: Verify your Directus URL and token are correct
- Schema Sync Failures: Ensure your Directus user has admin permissions
- Connection Issues: Check that your Directus instance is accessible

The server logs errors to stderr. You can check the logs in your AI assistant's console or terminal.

- Store your Directus token securely
- Use environment variables for sensitive configuration
- Consider using a dedicated service account for the MCP server
- Regularly rotate your API tokens
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request

MIT License - see LICENSE file for details

Process Street MCP Server. Connect AI agents to workflows, tasks, runs, datasets, and form fields via a hosted OAuth endpoint. Trigger compliance checklists, complete approvals, and pull audit-grade operational data. Works with Claude, Cursor, ChatGPT, Windsurf, Cline, and any MCP-compatible client. SOC 2, HIPAA, GDPR.

Qasper gives AI agents the tools to discover local service businesses, check availability, and book appointments in real time.

Keep teams & agents coordinated automatically

Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.

A multi-client AI agent monitoring and control system with automatic task completion detection.

An MCP server for AI-to-AI collaboration, enabling autonomous workflows and role-based task management between different AI models.

Connects Claude to WordPress sites to create posts and manage sites using the WordPress REST API.

The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.

Shared workspace your AI agents write to — 184+ MCP tools for CMMN case management.