TickTick MCP Server
Enables interaction with TickTick task management system through MCP, allowing users to view, create, update, complete, and delete tasks and projects via natural language.
README
TickTick MCP Server
A Model Context Protocol (MCP) server for TickTick that enables interacting with your TickTick task management system directly through Claude and other MCP clients.
Features
- š View all your TickTick projects and tasks
- āļø Create new projects and tasks through natural language
- š Update existing task details (title, content, dates, priority)
- ā Mark tasks as complete
- šļø Delete tasks and projects
- š Full integration with TickTick's open API
- š Seamless integration with Claude and other MCP clients
Prerequisites
- Python 3.10 or higher
- uv - Fast Python package installer and resolver
- TickTick account with API access
- TickTick API credentials (Client ID, Client Secret, Access Token)
Installation
-
Clone this repository:
git clone https://github.com/jacepark12/ticktick-mcp.git cd ticktick-mcp -
Install with uv:
# Install uv if you don't have it already curl -LsSf https://astral.sh/uv/install.sh | sh # Create a virtual environment uv venv # Activate the virtual environment # On macOS/Linux: source .venv/bin/activate # On Windows: .venv\Scripts\activate # Install the package uv pip install -e . -
Authenticate with TickTick:
# Run the authentication flow uv run -m ticktick_mcp.cli authThis will:
- Ask for your TickTick Client ID and Client Secret
- Open a browser window for you to log in to TickTick
- Automatically save your access tokens to a
.envfile
-
Test your configuration:
uv run test_server.pyThis will verify that your TickTick credentials are working correctly.
Authentication with TickTick
This server uses OAuth2 to authenticate with TickTick. The setup process is straightforward:
-
Register your application at the TickTick Developer Center
- Set the redirect URI to
http://localhost:8000/callback - Note your Client ID and Client Secret
- Set the redirect URI to
-
Run the authentication command:
uv run -m ticktick_mcp.cli auth -
Follow the prompts to enter your Client ID and Client Secret
-
A browser window will open for you to authorize the application with your TickTick account
-
After authorizing, you'll be redirected back to the application, and your access tokens will be automatically saved to the
.envfile
The server handles token refresh automatically, so you won't need to reauthenticate unless you revoke access or delete your .env file.
Authentication with Dida365
껓ēęø å - Dida365 is China version of TickTick, and the authentication process is similar to TickTick. Follow these steps to set up Dida365 authentication:
-
Register your application at the Dida365 Developer Center
- Set the redirect URI to
http://localhost:8000/callback - Note your Client ID and Client Secret
- Set the redirect URI to
-
Add environment variables to your
.envfile:TICKTICK_BASE_URL='https://api.dida365.com/open/v1' TICKTICK_AUTH_URL='https://dida365.com/oauth/authorize' TICKTICK_TOKEN_URL='https://dida365.com/oauth/token' -
Follow the same authentication steps as for TickTick
Usage with Claude for Desktop
-
Install Claude for Desktop
-
Edit your Claude for Desktop configuration file:
macOS:
nano ~/Library/Application\ Support/Claude/claude_desktop_config.jsonWindows:
notepad %APPDATA%\Claude\claude_desktop_config.json -
Add the TickTick MCP server configuration, using absolute paths:
{ "mcpServers": { "ticktick": { "command": "<absolute path to uv>", "args": ["run", "--directory", "<absolute path to ticktick-mcp directory>", "-m", "ticktick_mcp.cli", "run"] } } } -
Restart Claude for Desktop
Once connected, you'll see the TickTick MCP server tools available in Claude, indicated by the šØ (tools) icon.
Available MCP Tools
| Tool | Description | Parameters |
|---|---|---|
get_projects |
List all your TickTick projects | None |
get_project |
Get details about a specific project | project_id |
get_project_tasks |
List all tasks in a project | project_id |
get_task |
Get details about a specific task | project_id, task_id |
create_task |
Create a new task | title, project_id, content (optional), start_date (optional), due_date (optional), priority (optional) |
update_task |
Update an existing task | task_id, project_id, title (optional), content (optional), start_date (optional), due_date (optional), priority (optional) |
complete_task |
Mark a task as complete | project_id, task_id |
delete_task |
Delete a task | project_id, task_id |
create_project |
Create a new project | name, color (optional), view_mode (optional) |
delete_project |
Delete a project | project_id |
Task-specific MCP Tools
Task Retrieval & Search
| Tool | Description | Parameters |
|---|---|---|
get_all_tasks |
Get all tasks from all projects | None |
get_tasks_by_priority |
Get tasks filtered by priority level | priority_id (0: None, 1: Low, 3: Medium, 5: High) |
search_tasks |
Search tasks by title, content, or subtasks | search_term |
Date-Based Task Retrieval
| Tool | Description | Parameters |
|---|---|---|
get_tasks_due_today |
Get all tasks due today | None |
get_tasks_due_tomorrow |
Get all tasks due tomorrow | None |
get_tasks_due_in_days |
Get tasks due in exactly X days | days (0 = today, 1 = tomorrow, etc.) |
get_tasks_due_this_week |
Get tasks due within the next 7 days | None |
get_overdue_tasks |
Get all overdue tasks | None |
Getting Things Done (GTD) Framework
| Tool | Description | Parameters |
|---|---|---|
get_engaged_tasks |
Get "engaged" tasks (high priority or overdue) | None |
get_next_tasks |
Get "next" tasks (medium priority or due tomorrow) | None |
batch_create_tasks |
Create multiple tasks at once | tasks (list of task dictionaries) |
Example Prompts for Claude
Here are some example prompts to use with Claude after connecting the TickTick MCP server:
General
- "Show me all my TickTick projects"
- "Create a new task called 'Finish MCP server documentation' in my work project with high priority"
- "List all tasks in my personal project"
- "Mark the task 'Buy groceries' as complete"
- "Create a new project called 'Vacation Planning' with a blue color"
- "When is my next deadline in TickTick?"
Task Filtering Queries
- "What tasks do I have due today?"
- "Show me everything that's overdue"
- "Show me all tasks due this week"
- "Search for tasks about 'project alpha'"
- "Show me all tasks with 'client' in the title or description"
- "Show me all my high priority tasks"
GTD Workflow
Following David Allen's "Getting Things Done" framework, manage an Engaged and Next actions.
- Engaged will retrieve tasks of high priority, due today or overdue.
- Next will retrieve medium priority or due tomorrow.
- Break down complex actions into smaller actions with batch_creation
For example:
- "Time block the rest of my day from 2-8pm with items from my engaged list"
- "Walk me through my next actions and help my identify what I should focus on tomorrow?"
- "Break down this project into 5 smaller actionable tasks"
Development
Project Structure
ticktick-mcp/
āāā .env.template # Template for environment variables
āāā README.md # Project documentation
āāā requirements.txt # Project dependencies
āāā setup.py # Package setup file
āāā test_server.py # Test script for server configuration
āāā ticktick_mcp/ # Main package
āāā __init__.py # Package initialization
āāā authenticate.py # OAuth authentication utility
āāā cli.py # Command-line interface
āāā src/ # Source code
āāā __init__.py # Module initialization
āāā auth.py # OAuth authentication implementation
āāā server.py # MCP server implementation
āāā ticktick_client.py # TickTick API client
Authentication Flow
The project implements a complete OAuth 2.0 flow for TickTick:
- Initial Setup: User provides their TickTick API Client ID and Secret
- Browser Authorization: User is redirected to TickTick to grant access
- Token Reception: A local server receives the OAuth callback with the authorization code
- Token Exchange: The code is exchanged for access and refresh tokens
- Token Storage: Tokens are securely stored in the local
.envfile - Token Refresh: The client automatically refreshes the access token when it expires
This simplifies the user experience by handling the entire OAuth flow programmatically.
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
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.