Ticktick MCP Server

@dev-mirzabicer

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

dev-mirzabicer

提交者

MirzaBicer

关于 Ticktick MCP Server

A fully-featured MCP server for TickTick

#ticktick #mcp #python-sdk

Ticktick MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "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"
      }
    }
  }
}

Ticktick MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Ticktick Mcp?

Ticktick Mcp is an MCP (Model Context Protocol) server built on the ticktick-sdk Python library that enables AI assistants like Claude and GPT to manage TickTick tasks programmatically. It provides 45 tools covering task management, project organization, habits, focus/pomodoro, tags, and more, routing operations automatically between TickTick's official V1 API and the undocumented V2 API.

How to use Ticktick Mcp?

Install via pip install ticktick-sdk with Python 3.11+. Configure authentication by registering an OAuth2 app on the TickTick Developer Portal and creating a .env file with your client ID, secret, redirect URI, access token, username, and password. Run python scripts/get_oauth_token.py for the token, then verify with python -c .... The MCP server can then be invoked through any MCP-compatible host; the library itself exposes 45 tools for AI assistants.

Key features of Ticktick Mcp

45 MCP tools covering all TickTick features
Dual output: Markdown for humans, JSON for machines
Async-first with full Pydantic v2 validation
Unified routing to V1 (OAuth2) and V2 (session) APIs
Full habit CRUD with check-ins, streaks, and goals
Focus/pomodoro session data and statistics
300+ tests with comprehensive type hints

Use cases of Ticktick Mcp

Let an AI assistant create, update, complete, and move tasks in TickTick.
Query tasks by tag, priority, due date, or search term via natural language.
Manage projects, folders, and kanban boards programmatically.
Track habits with check-ins and streak analytics through AI.
Access productivity stats and focus session data.

常见问题

What are the runtime requirements for Ticktick Mcp?

Python 3.11+ and a TickTick account (free or Pro). For full functionality, both OAuth2 app registration and account credentials are required.

How does Ticktick Mcp handle TickTick’s two APIs?

It combines the official V1 OAuth2 API and the undocumented V2 session API, automatically routing each operation to the appropriate API based on the feature needed.

Where do my credentials and data live?

All credentials are stored locally in a `.env` file. Data is accessed via TickTick’s APIs; the server does not store data externally.

What transport does Ticktick Mcp use?

The README does not specify the transport protocol beyond MCP compatibility; it is designed to work with MCP-compatible AI assistants.

How is Ticktick Mcp different from other TickTick libraries?

It is the only library that includes an MCP server, provides async support with Pydantic v2, full habit CRUD, focus/pomodoro access, and automatic V1/V2 routing.

开发工具分类下的更多 MCP 服务器

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Total CMS

Joe Workman

Read-only Total CMS docs and site content over MCP: exact Twig signatures, field types, schema options, the CLI, release notes and comparisons. No key required.

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP