What are the prerequisites?
Python 3.10 or higher, `uv` (fast package installer), and a TickTick account with API credentials (Client ID, Client Secret, Access Token).
@jacepark12
基本信息
MCP server that interacts with TickTick (Dida 365) via the TickTick Open API
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ticktick-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}
}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。
A Model Context Protocol server that lets you manage your TickTick tasks and projects directly through Claude or any other MCP client, using TickTick’s open API.
Install the package with uv, run the OAuth2 authentication command (uv run -m ticktick_mcp.cli auth), and configure Claude for Desktop by adding the server entry to claude_desktop_config.json. Once connected, MCP tools become available in the client.
Python 3.10 or higher, `uv` (fast package installer), and a TickTick account with API credentials (Client ID, Client Secret, Access Token).
The server uses OAuth2. Running `uv run -m ticktick_mcp.cli auth` opens a browser to authorize your account, then automatically saves the tokens in a `.env` file. Token refresh is handled automatically.
Yes. Set environment variables for the Dida365 API URLs before authentication, then follow the same OAuth2 steps.
The server works with any MCP client, including Claude for Desktop. Configuration requires adding the server to the client's MCP settings file.
API tokens are stored locally in a `.env` file. All task data resides on TickTick’s servers and is accessed via their official API.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Open-source MCP to use Blender with any LLM

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.
评论