partymola/ticktick-mcp
🐍 ☁️ 🏠 - MCP server for TickTick task management: create, update, complete, move, and filter tasks with field-preserving updates and completion tracking.
Quick Install
{
"mcpServers": {
"partymola-ticktick-mcp": {
"command": "npx",
"args": [
"-y",
"partymola-ticktick-mcp"
]
}
}
}Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.
Documentation Overview
ticktick-mcp
MCP server for TickTick task management. Create, update, complete, move, and filter tasks via the TickTick v2 API, with field-preserving updates, day-of-week date validation, read-after-write verification, and idempotent completion tracking.
Designed for Claude Code and other MCP clients.
Unofficial. Not affiliated with TickTick Ltd. Built on ticktick-py (MIT).
Features
- Full task lifecycle - create, update, complete, move, subtask, and delete
- Field-preserving updates -
ticktick_update_taskre-fetches the task and overlays only the fields you set, so the API never wipes the ones you omit - Day-of-week validation - any call that sets a date must confirm the weekday, catching off-by-one date mistakes before they reach the server
- Read-after-write verification - create/update re-read the task and surface
_verification_warningswhen the server echo doesn't match - Compact listing - list tools return a trimmed view by default so large projects stay under the MCP result-size cap (see below)
- Fresh reads - read tools re-sync server state on demand, so edits made from the TickTick app on other devices show up without a restart
- Completion tracking - mark completed tasks as processed so an agent reviews each one exactly once
Requirements
- Python 3.13+
- uv (recommended - see the install note below)
- A TickTick account
- A registered TickTick app for OAuth credentials (free - developer.ticktick.com)
Install
git clone https://github.com/partymola/ticktick-mcp
cd ticktick-mcp
uv sync
This creates a .venv and installs from uv.lock, giving you the console script at .venv/bin/ticktick-mcp.
Use uv, not plain
pip. This server depends on a fork ofticktick-pypinned via[tool.uv.sources]/uv.lock.uvhonours that pin; a plainpip install .silently resolves the bareticktick-pyname from PyPI instead, giving you the upstream package without this project's fixes.
Credentials
TickTick sign-in needs two things: an OAuth app (client ID + secret) and your own account login.
-
Register an app at developer.ticktick.com. Set the Redirect URI to
http://localhost:8080/redirect. Note the Client ID and Client Secret. -
Copy the template and fill it in:
cp .env.example .envTICKTICK_CLIENT_ID=your_client_id TICKTICK_CLIENT_SECRET=your_client_secret TICKTICK_REDIRECT_URI=http://localhost:8080/redirect TICKTICK_USERNAME=your_ticktick_email TICKTICK_PASSWORD=your_ticktick_password
There is no separate auth step. The server logs in lazily on the first tool call (username/password via ticktick-py, plus the OAuth token), then caches the OAuth token next to your .env as .token-oauth and refreshes it automatically.
The server looks for .env in this order: the --dotenv-dir <path> argument, then the TICKTICK_MCP_DOTENV_DIR environment variable, then ~/.config/ticktick-mcp/. If no .env is found it falls back to the TICKTICK_* environment variables directly, which is convenient for container/CI use.
Privacy and the unofficial API
Your TickTick credentials live only in your local .env (or the environment) and are sent only to TickTick's own servers - never to the developer or any third party. The server reads and writes only your own account.
This server uses TickTick's unofficial v2 API (via ticktick-py) rather than the official Open API. That is a deliberate choice: the official API has no list-completed-tasks endpoint, no tags, and no cross-project task listing - all of which this server relies on. See docs/why-not-the-official-api.md for the full rationale, the risk trade-off, and the triggers that would make us reconsider.
Register with Claude Code
claude mcp add -s user ticktick -- /path/to/ticktick-mcp/.venv/bin/ticktick-mcp --dotenv-dir /path/to/config
--dotenv-dir is optional if your .env lives in ~/.config/ticktick-mcp/ or you supply the TICKTICK_* variables through the environment.
Then ask Claude things like:
- "What's on my TickTick list for this week?"
- "Add a task to call the dentist on Friday at 9am."
- "Mark the grocery task as done."
- "Move the budget task to the Finance project."
CLI
ticktick-mcp Start the MCP server (stdio transport)
ticktick-mcp --dotenv-dir PATH Directory holding the .env file
ticktick-mcp --version Print the installed package version
The server has no other subcommands - it is the MCP server. All task operations happen through the MCP tools below.
MCP tools
| Tool | Description |
|---|---|
ticktick_create_task | Create a task, preserving date/reminder/priority/timezone fields; warns if no due date is set (no reminder would fire) |
ticktick_update_task | Update a task by overlaying only the fields you set onto the current server object (omitted fields are never wiped) |
ticktick_complete_task | Mark a task complete and re-verify; distinguishes a recurring task rolling forward from a normal completion |
ticktick_delete_tasks | Delete one or more tasks by ID |
ticktick_move_task | Move a task into a different project |
ticktick_make_subtask | Nest one task as a subtask of another in the same project |
ticktick_get_tasks_from_project | List every open task in a project (compact or full) |
ticktick_filter_tasks | Find tasks by any mix of project, priority, tag, status, and due/completion-date window |
ticktick_get_by_id | Look up any task, project, or tag by its full ID |
ticktick_get_all | Dump all projects or all tags from local state |
ticktick_sync | Force an immediate refresh of local state from the server |
ticktick_get_unprocessed_completions | List recently completed tasks in a project not yet marked processed |
ticktick_mark_completion_processed | Record that a completed task has been reviewed, excluding it from future checks |
ticktick_convert_datetime_to_ticktick_format | Convert an ISO 8601 datetime + IANA timezone to TickTick's wire format |
Projects: name or ID
Every tool that takes a project ID also takes the project's name - ticktick_create_task, ticktick_get_tasks_from_project, ticktick_update_task, ticktick_move_task, ticktick_delete_tasks, ticktick_filter_tasks, and both completion-tracking tools:
ticktick_create_task(title="Renew insurance", project_id="Home Admin")
Names match case-insensitively, ignoring surrounding whitespace, and "Inbox" resolves to your inbox. IDs keep working unchanged and always win, so nothing that works today changes.
The one new error is ambiguity: if two projects share a name, the call fails and names both IDs rather than picking one, since guessing would file the task somewhere you would not think to look. Anything else the server cannot resolve is passed to the API untouched, exactly as before.
The two completion-tracking tools are the exception: they refuse a project reference they cannot confirm rather than passing it on, because that value is the key their local database is written under. An unresolvable one would write a row no later lookup by ID can find. If the project list could not be refreshed to check, they say so (outcome: "project_list_unverifiable") instead of claiming the project does not exist.
Listing tasks: compact by default
The list-returning tools - ticktick_get_tasks_from_project and ticktick_filter_tasks - default to detail="compact". Compact output keeps the browsing-relevant fields (id, projectId, title, dueDate, startDate, priority, status, isAllDay, timeZone, tags) plus a contentPreview (the first ~200 chars of content), and drops the heavy content/desc/checklist items blobs and bulky sync metadata. This keeps large projects under the MCP result-size cap so the client does not have to spill the result to disk. Keyword search still works against title and contentPreview.
- Need the full objects? Pass
detail="full". - Need one task's full content? Use
ticktick_get_by_id. - Editing a task: fetch the full object with
ticktick_get_by_idfirst, then send every field back viaticktick_update_task. The TickTick API wipes any field omitted from an update, so compact output must never feed an update.
If a compact result would still exceed the size budget, the soonest-due tasks are returned and a final _truncation_note element reports how many were omitted - nothing is dropped silently. Reach the rest with a narrower ticktick_filter_tasks query, detail="full", or ticktick_get_by_id.
Freshness: reads stay current
The TickTick account can be edited from the app on other devices while the server runs. To keep reads from going stale, the read tools re-sync server state on demand, throttled to at most once per window (default 15s, override with TICKTICK_MCP_SYNC_TTL_SECONDS). A change made elsewhere becomes visible within that window; call ticktick_sync to force an immediate refresh and get the current task/project counts. If a sync fails, the last-known state is served rather than erroring - except in ticktick_get_all, which refreshes every call and reports the failure instead, since a full dump is the wrong place to serve a stale answer quietly.
Configuration
| Variable | Default | Description |
|---|---|---|
TICKTICK_MCP_DOTENV_DIR | ~/.config/ticktick-mcp/ | Directory holding the .env file (the --dotenv-dir argument takes precedence) |
TICKTICK_MCP_SYNC_TTL_SECONDS | 15 | Minimum seconds between on-demand read re-syncs |
TICKTICK_MCP_INIT_RETRY_SECONDS | 60 | Cooldown before retrying client login after a failed first connection |
TICKTICK_MCP_RATELIMIT_RETRY_SECONDS | 300 | Cooldown before retrying login after a rate-limit (HTTP 429); longer than the init cooldown because a 429 clears slowly and each retry prolongs it |
TICKTICK_MCP_PROTECTED_TASK_IDS | unset | Task IDs an agent must never modify, separated by spaces or commas. Every mutating tool refuses before sending anything; reads are unaffected. Unset means no protection. |
Protecting tasks from modification
Some tasks should never be changed by an agent, whatever it is asked to do. List their IDs in TICKTICK_MCP_PROTECTED_TASK_IDS:
TICKTICK_MCP_PROTECTED_TASK_IDS="60ca9dbc8f08516d9dd56324,60ca9dbc8f08516d9dd56325"
ticktick_update_task, ticktick_complete_task, ticktick_delete_tasks, ticktick_move_task and ticktick_make_subtask then refuse any call naming a protected task, returning outcome: "protected_task". No request that reads or writes the task is sent. A batch delete containing a protected ID is refused in full rather than partially applied, since a partial delete cannot be undone.
Because TickTick propagates delete and move through subtasks, delete, move and make_subtask also refuse when a protected task is the parent or the subtask of a task you named. That check refreshes local state first, so it adds one request per delete, move or reparent while protection is configured — and returns outcome: "protection_unverifiable" if that refresh fails, since it cannot rule out a protected subtask on a snapshot it could not update. With the variable unset it does no extra work at all. IDs are matched ignoring surrounding whitespace, quotes and case. Reading protected tasks always works.
Credentials (TICKTICK_CLIENT_ID, TICKTICK_CLIENT_SECRET, TICKTICK_REDIRECT_URI, TICKTICK_USERNAME, TICKTICK_PASSWORD) are read from the .env file or, if absent, directly from the environment.
Data safety
A pre-commit hook (scripts/check-no-data.sh) blocks accidentally committing databases, credentials, and large files - *.db and backup variants, anything under config/*.json / config/*.env (except *.example.*), and files over 100KB (except uv.lock). Install it after cloning:
ln -sf ../../scripts/check-no-data.sh .git/hooks/pre-commit
Contributing
See CONTRIBUTING.md for development setup, the test workflow, and the pre-commit hook. Changes are tracked in CHANGELOG.md.