About TickTick MCP Server
A TickTick MCP server for AI assistants that manage tasks and projects through the TickTick Open API. It supports task updates and completion as well as creating projects with configurable properties.
Key features
- 01Get tasks from one or all projects
- 02Create tasks with dates and priorities
- 03Update, complete, or delete tasks
- 04List existing projects
- 05Create projects with custom properties
Use cases
- 01Review tasks across TickTick projects
- 02Add tasks with due dates and priorities
- 03Update or complete tasks through an AI assistant
- 04Create projects for different work types
MCP support
The server exposes TickTick task and project operations as tools to MCP clients, using the TickTick Open API and an access token.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETickTick MCP Server
A Model Context Protocol (MCP) server implementation for TickTick, the popular task management application. This server allows AI assistants to interact with TickTick through the TickTick Open API.
📋 Features
- Get tasks from projects
- Create new tasks with details like due dates, priorities, and descriptions
- Update existing tasks
- Mark tasks as complete
- Delete tasks
- Get list of projects
- Create new projects with custom properties
🚀 Quick Start
Prerequisites
- Node.js (v18 or higher)
- TickTick Developer account
- TickTick API Access Token
Installation
-
Clone this repository:
git clone https://github.com/shidhincr/ticktick-mcpserver.git cd ticktick-mcpserver -
Install dependencies:
npm install -
Build the project:
npm run build -
Set the environment variable with your access token:
export TICKTICK_ACCESS_TOKEN=your_access_token_here -
Start the server:
npm start
🔑 Authentication Setup
1. Register a TickTick Developer Account
- Visit TickTick Developer Center
- Create an account and register your application
- Get the client ID and client secret
2. Get Access Token
Follow the OAuth2 flow to obtain an access token:
-
Redirect users to TickTick authorization page:
https://ticktick.com/oauth/authorize?scope=tasks:read tasks:write&client_id=YOUR_CLIENT_ID&state=STATE&redirect_uri=YOUR_REDIRECT_URI&response_type=code -
Exchange the received code for an access token: Make a POST request to
https://ticktick.com/oauth/tokenwith:- Header: Basic authentication with your client_id and client_secret
- Body (application/x-www-form-urlencoded):
- code: the received authorization code
- grant_type: authorization_code
- scope: tasks:read tasks:write
- redirect_uri: your redirect URI
-
Store the received access token securely.
🛠️ Available Tools
The server implements the following tools for AI interaction:
Task Management
-
ticktick_get_tasks- Get tasks from a specific project or all projects{ project_id?: string; // Optional project ID limit?: number; // Optional result limit (default: 10) } -
ticktick_create_task- Create a new task{ title: string; // Required: Task title content?: string; // Optional: Task content desc?: string; // Optional: Task description project_id: string; // Required: Project ID due_date?: string; // Optional: Due date (ISO format) priority?: number; // Optional: Priority (0, 1, 3, 5) is_all_day?: boolean; // Optional: All-day task flag } -
ticktick_update_task- Update an existing task{ project_id: string; // Required: Project ID task_id: string; // Required: Task ID title?: string; // Optional: New title // ... other task properties } -
ticktick_complete_task- Mark a task as complete{ project_id: string; // Required: Project ID task_id: string; // Required: Task ID } -
ticktick_delete_task- Delete a task{ project_id: string; // Required: Project ID task_id: string; // Required: Task ID }
Project Management
-
ticktick_get_projects- Get a list of all projects -
ticktick_create_project- Create a new project{ name: string; // Required: Project name color?: string; // Optional: Color code (e.g. "#F18181") view_mode?: string; // Optional: View mode ("list", "kanban", "timeline") kind?: string; // Optional: Project kind ("TASK", "NOTE") }
📁 Project Structure
ticktick-mcpserver/
├── dist/ # Compiled TypeScript (generated after building)
├── src/
│ └── index.ts # Main server implementation
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # Documentation
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📚 API Reference
This project uses the TickTick Open API. For detailed information about API endpoints and parameters, please refer to the official documentation.
📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgements
- TickTick for providing the API
- Model Context Protocol (MCP) for the protocol specification
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.