dida365 Agent Mcp

@linhai0872

About dida365 Agent Mcp

MCP server that connects AI agents (Claude Code, Cursor, Codex) to Dida365/TickTick. 40 tools for tasks, projects, tags, habits, folders, and search — manage everything through natural language.

#dida365 #ticktick #task-management #productivity #todo #ai-agent #python

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dida365": {
      "command": "uvx",
      "args": [
        "dida365-agent-mcp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is dida365 Agent Mcp?

dida365 Agent Mcp is an MCP (Model Context Protocol) server that provides 40 tools to interact with the Dida365 (China) and TickTick (International) task management platforms. It combines official V1 Open API tools with private V2 API tools for advanced features like tags, habits, folders, and parent tasks. Designed for developers and power users who want to automate task management via AI agents.

How to use dida365 Agent Mcp?

Run uvx --from dida365-agent-mcp dida365-oauth once to authenticate via a one-click browser OAuth flow. Then add the server to your MCP client configuration using uvx dida365-agent-mcp as the command and args. The token is saved locally and lasts approximately 180 days.

Key features of dida365 Agent Mcp

40 tools — 19 V1 (official Open API) + 21 V2 (private API)
Dual platform — supports Dida365 and TickTick via one environment variable
Dual transport — stdio for local clients, streamable-http for remote agents
One-click OAuth — automatic browser flow, token cached for ~180 days
Docker ready — deploy with a single docker compose up command

Use cases of dida365 Agent Mcp

Automate task creation, update, completion, and filtering across multiple projects
Manage tags, habits, folders, and parent-child task relationships
Search and move tasks using private V2 API endpoints
Integrate task management into AI agent workflows on both China and international platforms

FAQ from dida365 Agent Mcp

What is the difference between V1 and V2 tools?

V1 tools use the official Dida365/TickTick Open API and cover standard task and project operations. V2 tools use private APIs that enable extras like tags, habits, folders, and search.

How do I authenticate with the server?

Run uvx --from dida365-agent-mcp dida365-oauth once. This opens a browser for OAuth login and saves the token locally for repeated use (valid ~180 days).

Does it support both Dida365 and TickTick?

Yes. Set one environment variable to switch between Dida365 (China) and TickTick (International). Both platforms are fully supported.

What transports are available for the MCP server?

Two transports are supported: stdio for local client integration and streamable-http for remote agent connections.

Are there any runtime dependencies?

The server requires uvx to run. Docker is optional but recommended for simplified deployment via docker compose up.

Frequently asked questions

What is the difference between V1 and V2 tools?

V1 tools use the official Dida365/TickTick Open API and cover standard task and project operations. V2 tools use private APIs that enable extras like tags, habits, folders, and search.

How do I authenticate with the server?

Run `uvx --from dida365-agent-mcp dida365-oauth` once. This opens a browser for OAuth login and saves the token locally for repeated use (valid ~180 days).

Does it support both Dida365 and TickTick?

Yes. Set one environment variable to switch between Dida365 (China) and TickTick (International). Both platforms are fully supported.

What transports are available for the MCP server?

Two transports are supported: `stdio` for local client integration and `streamable-http` for remote agent connections.

Are there any runtime dependencies?

The server requires `uvx` to run. Docker is optional but recommended for simplified deployment via `docker compose up`.

Comments

Basic information

More AI & Agents MCP servers

mcp-hfspace MCP Server 🤗

evalstate

MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

387

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

Model Context Protocol Server for Home Assistant

tevonsb

A MCP server for Home Assistant

574

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468