ticktick-sdk: A TickTick MCP Server & Full Python SDK

A comprehensive async Python SDK for TickTick with MCP (Model Context Protocol) server support.

Use TickTick programmatically from Python, or let AI assistants manage your tasks.

Table of Contents

• Features
• Why This Library?
• Installation
• MCP Server Setup & Usage
• Step 1: Register Your App
• Step 2: Get OAuth2 Access Token
• Step 3: Configure Your AI Assistant
• CLI Reference
• Example Conversations
• Available MCP Tools
• Python Library Setup & Usage
• Setup
• Quick Start
• Tasks
• Projects & Folders
• Tags
• Habits
• Focus/Pomodoro
• User & Statistics
• Error Handling
• Architecture
• API Reference
• TickTick API Quirks
• Environment Variables
• Running Tests
• Troubleshooting
• Contributing

---

Features

MCP Server

• 43 Tools: Streamlined coverage of TickTick functionality
• Batch Operations: All mutations accept lists (1-100 items) for bulk operations
• AI-Ready: Works with Claude, GPT, and other MCP-compatible assistants
• Dual Output: Markdown for humans, JSON for machines

Python Library

• Full Async Support: Built on httpx for high-performance async operations
• Batch Operations: Create, update, delete, complete up to 100 tasks in a single call
• Complete Task Management: Create, read, update, delete, complete, move, pin tasks
• Kanban Boards: Full column management (create, update, delete, move tasks between columns)
• Project Organization: Projects, folders, kanban boards
• Tag System: Hierarchical tags with colors
• Habit Tracking: Full CRUD for habits with batch check-ins, streaks, and goals
• Focus/Pomodoro: Access focus session data and statistics
• User Analytics: Productivity scores, levels, completion rates

Developer Experience

• Type-Safe: Full Pydantic v2 validation with comprehensive type hints
• Well-Tested: 300+ tests covering both mock and live API interactions
• Documented: Extensive docstrings and examples

---

Why This Library?

The Two-API Problem

TickTick has two different APIs:

API	Type	What We Use It For
V1 (OAuth2)	Official, documented	Project with all tasks, basic operations
V2 (Session)	Unofficial, reverse-engineered	Tags, folders, habits, focus, subtasks, and more

The official V1 API is limited. Most of TickTick's power features (tags, habits, focus tracking) are only available through the undocumented V2 web API. This library combines both, routing each operation to the appropriate API automatically.

Compared to Other Libraries

Based on analysis of the actual source code of available TickTick Python libraries:

Feature	ticktick-sdk	pyticktick	ticktick-py	tickthon	ticktick-python
I/O Model	Async	Async	Sync	Sync	Sync
Type System	Pydantic V2	Pydantic V2	Dicts	attrs	addict
MCP Server	Yes	No	No	No	No
Habits	Full CRUD	No	Basic	Basic	No
Focus/Pomo	Yes	Yes	Yes	Yes	No
Unified V1+V2	Smart Routing	Separate	Both	V2 only	V2 only
Subtasks	Advanced	Batch	Yes	Basic	Basic
Tags	Full (merge/rename)	Yes	Yes	Yes	No

Key Differentiators:

• MCP Server: Only ticktick-sdk provides AI assistant integration via Model Context Protocol
• Unified API Routing: Automatically routes operations to V1 or V2 based on feature requirements
• Full Habit CRUD: Complete habit management including check-ins, streaks, archive/unarchive
• Async-First: Built on httpx for high-performance async operations

---

Installation

pip install ticktick-sdk

Requirements: - Python 3.11+ - TickTick account (free or Pro)

---

MCP Server Setup & Usage

Use TickTick with AI assistants like Claude through the Model Context Protocol.

Step 1: Register Your App

1. Go to the TickTick Developer Portal
2. Click "Create App"
3. Fill in:
4. App Name: e.g., "My TickTick MCP"
5. Redirect URI: http://127.0.0.1:8080/callback
6. Save your Client ID and Client Secret

Step 2: Get OAuth2 Access Token

Run the auth command with your credentials:

TICKTICK_CLIENT_ID=your_client_id \
TICKTICK_CLIENT_SECRET=your_client_secret \
ticktick-sdk auth

This will: 1. Open your browser to TickTick's authorization page 2. Authorize the app - Click "Authorize" to grant access 3. Return to terminal - After authorizing, you'll see output like this:

============================================================
  SUCCESS! Here is your access token:
============================================================

a]234abc-5678-90de-f012-34567890abcd

============================================================

NEXT STEPS:

For Claude Code users:
  Run (replace YOUR_* placeholders):
    claude mcp add ticktick \
      -e TICKTICK_CLIENT_ID=YOUR_CLIENT_ID \
      ...

1. Copy this token - You'll need it in the next step

Note: Sometimes the browser shows an "invalid credentials" error page. Just refresh the page and it should work.

SSH/Headless Users: Add --manual flag for a text-based flow that doesn't require a browser.

Step 3: Configure Your AI Assistant

Claude Code (Recommended)

claude mcp add ticktick \
  -e TICKTICK_CLIENT_ID=your_client_id \
  -e TICKTICK_CLIENT_SECRET=your_client_secret \
  -e TICKTICK_ACCESS_TOKEN=your_access_token \
  -e TICKTICK_USERNAME=your_email \
  -e TICKTICK_PASSWORD=your_password \
  -- ticktick-sdk

Note: For TICKTICK_ACCESS_TOKEN, paste the token you copied from Step 2.

Verify it's working:

claude mcp list        # See all configured servers
/mcp                   # Within Claude Code, check server status

Claude Desktop

Add to your Claude Desktop config:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ticktick": {
      "command": "ticktick-sdk",
      "env": {
        "TICKTICK_CLIENT_ID": "your_client_id",
        "TICKTICK_CLIENT_SECRET": "your_client_secret",
        "TICKTICK_ACCESS_TOKEN": "your_access_token",
        "TICKTICK_USERNAME": "your_email",
        "TICKTICK_PASSWORD": "your_password"
      }
    }
  }
}

Other MCP-Compatible Tools

This server works with any tool that supports the Model Context Protocol, which includes most modern AI assistants and IDEs. The configuration is similar - you just need to provide the command (ticktick-sdk) and the environment variables shown above.

CLI Reference

The ticktick-sdk command provides several subcommands:

Command	Description
ticktick-sdk	Start the MCP server (default)
ticktick-sdk server	Start the MCP server (explicit)
ticktick-sdk server --host HOST	Use specific API host (ticktick.com or dida365.com)
ticktick-sdk server --enabledModules MODULES	Enable only specific tool modules (comma-separated)
ticktick-sdk server --enabledTools TOOLS	Enable only specific tools (comma-separated)
ticktick-sdk auth	Get OAuth2 access token (opens browser)
ticktick-sdk auth --manual	Get OAuth2 access token (SSH-friendly)
ticktick-sdk --version	Show version information
ticktick-sdk --help	Show help message

Tool Filtering (reduces context window usage for AI assistants):

# Enable only task and project tools
ticktick-sdk server --enabledModules tasks,projects

# Enable specific tools only
ticktick-sdk server --enabledTools ticktick_create_tasks,ticktick_list_tasks

# Available modules: tasks, projects, folders, columns, tags, habits, user, focus

Example Conversations

Once configured, you can ask Claude things like:

• "What tasks do I have due today?"
• "Create a task to call John tomorrow at 2pm"
• "Show me my high priority tasks"
• "Mark the grocery shopping task as complete"
• "What's my current streak for the Exercise habit?"
• "Check in my meditation habit for today"
• "Create a new habit to drink 8 glasses of water daily"

Available MCP Tools (43 Total)

All mutation tools accept lists for batch operations (1-100 items).

Task Tools (Batch-Capable)

Tool	Description
ticktick_create_tasks	Create 1-50 tasks with titles, dates, tags, etc.
ticktick_get_task	Get task details by ID
ticktick_list_tasks	List tasks (active/completed/abandoned/deleted via status filter)
ticktick_update_tasks	Update 1-100 tasks (includes column assignment)
ticktick_complete_tasks	Complete 1-100 tasks
ticktick_delete_tasks	Delete 1-100 tasks (moves to trash)
ticktick_move_tasks	Move 1-50 tasks between projects
ticktick_set_task_parents	Set parent-child relationships for 1-50 tasks
ticktick_unparent_tasks	Remove parent relationships from 1-50 tasks
ticktick_search_tasks	Search tasks by text
ticktick_pin_tasks	Pin or unpin 1-100 tasks

Project Tools

Tool	Description
ticktick_list_projects	List all projects
ticktick_get_project	Get project details with tasks
ticktick_create_project	Create a new project
ticktick_update_project	Update project properties
ticktick_delete_project	Delete a project

Folder Tools

Tool	Description
ticktick_list_folders	List all folders
ticktick_create_folder	Create a folder
ticktick_rename_folder	Rename a folder
ticktick_delete_folder	Delete a folder

Kanban Column Tools

Tool	Description
ticktick_list_columns	List columns for a kanban project
ticktick_create_column	Create a kanban column
ticktick_update_column	Update column name or order
ticktick_delete_column	Delete a kanban column

Tag Tools

Tool	Description
ticktick_list_tags	List all tags
ticktick_create_tag	Create a tag with color
ticktick_update_tag	Update tag properties (includes rename via label)
ticktick_delete_tag	Delete a tag
ticktick_merge_tags	Merge two tags

Habit Tools (Batch-Capable)

Tool	Description
ticktick_habits	List all habits
ticktick_habit	Get habit details
ticktick_habit_sections	List sections (morning/afternoon/night)
ticktick_create_habit	Create a new habit
ticktick_update_habit	Update habit properties (includes archive/unarchive)
ticktick_delete_habit	Delete a habit
ticktick_checkin_habits	Check in 1-50 habits (supports backdating)
ticktick_habit_checkins	Get check-in history

User & Analytics Tools

Tool	Description
ticktick_get_profile	Get user profile
ticktick_get_status	Get account status
ticktick_get_statistics	Get productivity stats
ticktick_get_preferences	Get user preferences
ticktick_focus_heatmap	Get focus heatmap data
ticktick_focus_by_tag	Get focus time by tag

---

Python Library Setup & Usage

Use TickTick programmatically in your Python applications.

Setup

Step 1: Register Your App

Same as MCP setup - go to the TickTick Developer Portal and create an app.

Step 2: Create Your .env File

Create a .env file in your project directory:

# V1 API (OAuth2)
TICKTICK_CLIENT_ID=your_client_id_here
TICKTICK_CLIENT_SECRET=your_client_secret_here
TICKTICK_REDIRECT_URI=http://127.0.0.1:8080/callback
TICKTICK_ACCESS_TOKEN=  # Will be filled in Step 3

# V2 API (Session)
TICKTICK_USERNAME=your_ticktick_email@example.com
TICKTICK_PASSWORD=your_ticktick_password

# Optional
TICKTICK_TIMEOUT=30

Step 3: Get OAuth2 Access Token

# Source your .env file first, or export the variables
ticktick-sdk auth

Copy the access token to your .env file.

Step 4: Verify Setup

import asyncio
from ticktick_sdk import TickTickClient

async def test():
    async with TickTickClient.from_settings() as client:
        profile = await client.get_profile()
        print(f'Connected as: {profile.display_name}')

asyncio.run(test())

Quick Start

```python import async