tick-mcp
Enables AI assistants to manage TickTick tasks, projects, habits, tags, and focus stats using 71 tools via the Model Context Protocol.
README
tick-mcp
MCP server for TickTick — manage tasks, projects, habits, tags, focus stats, and more through the Model Context Protocol.
71 tools exposed over MCP, covering both the official TickTick Open API (V1) and the unofficial web API (V2) for features not yet available publicly.
Features
| Category | Tools |
|---|---|
| Tasks | create_task · update_task · complete_task · reopen_task · delete_task · get_task_detail · get_project_tasks · get_inbox · get_all_tasks |
| Batch | batch_create_tasks · batch_update_tasks · batch_delete_tasks · move_tasks |
| Projects | create_project · update_project · delete_project · get_project_detail · list_projects |
| Query / Search | workspace_map · query_projects · query_folders · query_tasks · query_notes · query_agenda · query_task_history · list_query_presets · save_query_preset · run_query_preset · delete_query_preset |
| Views | tasks_of_today · events_of_today · week_agenda · week_overview · upcoming_tasks · overdue_tasks · stale_tasks · priority_dashboard |
| Verified Actions | create_subtask · verified_create_project · verified_set_subtask_parent · verified_move_tasks · verified_batch_move · verified_assign_project_folder |
| Tags | create_tag · update_tag · rename_tag · merge_tags · delete_tag · list_tags |
| Habits | create_habit · update_habit · delete_habit · list_habits · habit_checkin · get_habit_records · list_habit_sections |
| Kanban | list_columns · manage_columns |
| Folders | list_project_folders · manage_project_folders |
| Focus | get_focus_stats |
| History | get_completed_tasks · get_deleted_tasks |
| Subtasks | set_subtask_parent |
| Sync / Stats | full_sync · get_user_status · get_productivity_stats |
| Utilities | ticktick_guide · check_v2_availability · build_recurrence_rule · build_reminder |
Query / Search highlights
- Structured task filtering — folders, projects, tags, parent/subtask shape, reminders, recurrence, checklist presence, and priorities.
- Time-aware agenda access — query by date range, datetime range, and HH:MM time windows without forcing a full sync first.
- Grep-like matching — substring search,
any/all/phrasekeyword modes, regex, and exclusion regex across chosen fields. - Targeted note search — notes are fetched only from NOTE projects in scope instead of materializing the whole workspace.
- Workspace navigation — folder/project map with optional active task counts to inspect the account structure before acting.
- Ready-made operational views — day view, week window, upcoming due tasks, overdue/stale detection, and priority summaries built on the same filter engine.
- Saved query presets — persist reusable task/note/agenda/history/week-overview queries and execute them later without rebuilding the filter set.
Verified workflow helpers
- Subtask-safe creation —
create_subtaskcreates the child, links it, then verifiesparentIdandchildIds. - Move verification —
verified_move_tasksre-reads destination projects and confirms every moved task is actually there. - Folder assignment verification —
verified_assign_project_folderverifies the persistedgroupIdthrough V2 sync, not through the misleading V1 response.
Intent-first discovery
ticktick_guide() supports both technical categories and real user goals.
- Category-oriented:
ticktick_guide(category="tasks")
- Intent-oriented:
ticktick_guide(intent="know_what_to_do_today")ticktick_guide(intent="plan_the_week")ticktick_guide(intent="find_a_note")ticktick_guide(intent="reorganize_projects")ticktick_guide(intent="clean_up_tasks")
Package Layout
src/tick_mcp/
├── mcp_api/
│ ├── core.py # shared FastMCP instance, catalog, helpers
│ ├── utilities.py # discovery + helper tools
│ ├── projects.py # project CRUD tools
│ ├── tasks_read.py # inbox / project / task reads
│ ├── tasks_write.py # task mutation tools
│ ├── tasks_batch.py # batch + structural task operations
│ ├── read.py # high-level query/search, views, and saved presets
│ ├── verified.py # safe wrappers with read-back verification + rollback hints
│ ├── folders.py # folders + kanban columns
│ ├── tags.py # tag tools
│ ├── habits.py # habit tools
│ ├── history.py # completed / deleted history
│ └── stats.py # focus and user/productivity stats
├── services/
│ └── query.py # reusable filtering, range and grep-like planning
├── client_api/
│ ├── transport.py # auth, sessions, low-level V1/V2 HTTP helpers
│ ├── projects.py # projects, folders, columns, tags
│ ├── tasks.py # tasks, sync, batch, history
│ ├── habits.py # habits and check-ins
│ └── stats.py # focus and user/productivity stats
├── client.py # stable public facade over client_api/*
├── models.py # pydantic contracts
├── server.py # stable public import surface for the MCP server
└── main.py # CLI entrypoint
Installation
# recommended — installs as a standalone tool
uv tool install tick-mcp
# or via pip
pip install tick-mcp
This provides two commands:
| Command | Description |
|---|---|
tick-mcp |
Start the MCP server (stdio transport) |
tick-admin |
CLI helper — session refresh, diagnostics |
Configuration
1. Environment variables
Copy the example file and fill in your tokens:
cp src/tick_mcp/.env.example src/tick_mcp/.env
| Variable | Required | Description |
|---|---|---|
TICKTICK_API_TOKEN |
Yes | V1 Open API bearer token (PAT or OAuth2) |
TICKTICK_SESSION_TOKEN |
No | V2 session cookie for extended features |
Getting a V1 token (simplest):
- Open TickTick → Settings → Integrations → API
- Copy the displayed Personal Access Token
Getting a V2 session token:
- Log in to ticktick.com in your browser
- DevTools → Application → Cookies → copy the
tcookie value
Or use the CLI to auto-login:
tick-admin session refresh
2. Server config
Runtime settings live in src/tick_mcp/config.yaml — API endpoints, timeouts, and user-agent are all externalised there.
MCP Client Integration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or ~/.config/Claude/claude_desktop_config.json (Linux):
{
"mcpServers": {
"ticktick": {
"command": "tick-mcp",
"env": {
"TICKTICK_API_TOKEN": "your-v1-token",
"TICKTICK_SESSION_TOKEN": "your-v2-token"
}
}
}
}
VS Code (GitHub Copilot)
Add to .vscode/mcp.json:
{
"servers": {
"ticktick": {
"command": "tick-mcp",
"env": {
"TICKTICK_API_TOKEN": "your-v1-token",
"TICKTICK_SESSION_TOKEN": "your-v2-token"
}
}
}
}
Other MCP clients
Any client that supports the stdio transport can launch tick-mcp as a subprocess.
Development
# Clone & install dev deps
git clone https://github.com/kpihx/tick-mcp.git
cd tick-mcp
uv sync --group dev
# Unit tests (155 selected unit tests, no network)
uv run pytest
# Live tests against real TickTick API (requires tokens in .env)
uv run pytest -m live
Test suite
- 155 selected unit tests — pure logic, mocked HTTP, zero network
- 12 live integration scripts — 508 assertions against the real TickTick API
License
MIT © 2025 Ivann KAMDEM
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.