TickTick MCP Server
Enables AI assistants to manage TickTick tasks and projects through OAuth2 authentication, supporting task creation, updates, completion, project management, and smart daily scheduling based on priorities and due dates.
README
<div align="center">
TickTick MCP Server 🎯
TickTick.com | Manage Your Tasks with AI
</div>
A comprehensive MCP (Model Context Protocol) server for managing your TickTick tasks directly from Claude or any MCP-compatible AI assistant.
Features ✨
- Task Management: Create, update, complete, and delete tasks
- Project Management: Create and manage projects/lists
- Smart Scheduling: Generate daily schedules based on task priorities and due dates
- OAuth2 Authentication: Secure authentication with TickTick's official API
- Rich Formatting: Beautiful markdown output for easy reading
Prerequisites
- Python 3.10 or higher
- A TickTick account
- A TickTick Developer App (we'll create this below)
Installation
Step 1: Clone/Copy the Server
# Create directory
mkdir -p ~/ticktick-mcp
cd ~/ticktick-mcp
# Copy the files (ticktick_mcp.py and pyproject.toml)
Step 2: Install Dependencies
# Using pip
pip install mcp httpx pydantic
# Or using the project
cd ~/ticktick-mcp
pip install -e .
Step 3: Register a TickTick Developer App
- Go to TickTick Developer Portal
- Log in with your TickTick account
- Click "+ App Name" to create a new app
- Enter a name (e.g., "Claude MCP Integration")
- Important: Set the OAuth Redirect URL to:
http://127.0.0.1:8080/callback - Click Save
- Note down your Client ID and Client Secret
Configuration
For Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ticktick": {
"command": "python",
"args": ["/path/to/ticktick-mcp/ticktick_mcp.py"],
"env": {}
}
}
}
Using uv (recommended):
{
"mcpServers": {
"ticktick": {
"command": "uv",
"args": ["run", "--directory", "/path/to/ticktick-mcp", "python", "ticktick_mcp.py"]
}
}
}
For Other MCP Clients
Run the server directly:
python ticktick_mcp.py
First-Time Setup (OAuth Authentication)
Once the MCP server is connected, use these tools in order:
1. Configure Credentials
Tell Claude:
"Configure TickTick with my credentials: Client ID is
YOUR_CLIENT_IDand Client Secret isYOUR_CLIENT_SECRET"
This will:
- Save your credentials securely
- Generate an authorization URL for you to visit
2. Authorize the App
- Claude will provide an authorization URL
- Open the URL in your browser
- Log in to TickTick and click "Allow"
- You'll be redirected to a URL like:
http://127.0.0.1:8080/callback?code=ABCD1234&state=mcp_auth - Copy the code parameter (
ABCD1234in this example)
3. Complete Authorization
Tell Claude:
"Complete TickTick authorization with code: ABCD1234"
You're now authenticated! The token is cached for ~6 months.
Available Tools
Authentication
| Tool | Description |
|---|---|
ticktick_configure |
Configure API credentials |
ticktick_authorize |
Complete OAuth flow |
ticktick_check_auth |
Check authentication status |
Tasks
| Tool | Description |
|---|---|
ticktick_list_tasks |
List all incomplete tasks |
ticktick_get_task |
Get details of a specific task |
ticktick_create_task |
Create a new task |
ticktick_update_task |
Update an existing task |
ticktick_complete_task |
Mark a task as complete |
ticktick_delete_task |
Delete a task |
Projects
| Tool | Description |
|---|---|
ticktick_list_projects |
List all projects/lists |
ticktick_create_project |
Create a new project |
ticktick_delete_project |
Delete a project |
Scheduling
| Tool | Description |
|---|---|
ticktick_schedule_time |
Generate a daily schedule |
ticktick_get_today |
Quick view of today's tasks |
Usage Examples
List Your Tasks
"Show me all my TickTick tasks"
Create a Task
"Create a TickTick task: Review Q4 report, due tomorrow, high priority"
Schedule Your Day
"Help me plan my day based on my TickTick tasks"
Create a Project
"Create a new TickTick project called 'Side Business Ideas'"
Complete a Task
"Mark task ID abc123 in project xyz as complete"
Task Priority Levels
| Priority | Value | Emoji |
|---|---|---|
| None | 0 | ⚪ |
| Low | 1 | 🟢 |
| Medium | 3 | 🟡 |
| High | 5 | 🔴 |
File Locations
The server stores configuration and tokens in your home directory:
- Configuration:
~/.ticktick-mcp-config.json - OAuth Token:
~/.ticktick-mcp-token.json
To reset authentication, delete these files.
Troubleshooting
"Not authenticated" Error
Run ticktick_check_auth to verify your authentication status, then re-run the OAuth flow if needed.
"Token expired" Error
Delete ~/.ticktick-mcp-token.json and re-authenticate.
"Rate limit exceeded" Error
Wait a minute before making more requests. TickTick has API rate limits.
"Resource not found" Error
Double-check the task ID and project ID. Use ticktick_list_tasks to see valid IDs.
API Reference
This server uses TickTick's official Open API:
Contributing
Feel free to extend this server! Some ideas:
- Add support for habits
- Add Pomodoro timer integration
- Add calendar view
- Add recurring task support
- Add tag management tools
License
MIT License - feel free to use and modify!
Built with ❤️ for productivity enthusiasts using Claude and TickTick.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。