dida365-agent
Provides tools to manage tasks, projects, tags, and habits on TickTick (and its Chinese counterpart Dida365) via CLI, Agent Skill, or MCP server, supporting full task management, project CRUD, full-text search, and habit check-ins.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dida365-agent Create a high-priority task to review the design doc by Friday"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Let AI agents manage Dida365 / TickTick tasks, projects, tags, and habits through natural language. Three form factors: a lightweight CLI, a ready-to-install Agent Skill, and a standard MCP Server.
No install required — run it directly with uvx. Supports both Dida365 (China) and TickTick (International), switchable with one env var.
Features
Related MCP server: TickTick MCP Server
Quick Start
Option 1: Use the CLI directly
No install needed — run with uvx (requires uv). First prepare credentials per the configuration guide and write them to .env:
# Browser OAuth (saves token, ~180 days)
uvx dida365-agent dida auth login
# List all projects
uvx dida365-agent dida project list
# Create a high-priority task due tomorrow
uvx dida365-agent dida task create --title "Review PR" --project <projectId> \
--priority 5 --due-date "2026-05-30T18:00:00+0800"
# Full-text search (V2)
uvx dida365-agent dida search "meeting"After installing locally (
uv tool install dida365-agent), use the shorterdidacommand.
Option 2: Use as an Agent Skill
Install the Skill in any Skill-compatible AI tool (Claude Code, Cursor, etc.) and drive it with natural language:
# Install the Skill
npx skills add linhai0872/dida365-agentThen just describe what you need in the AI chat:
Tidy up my unfinished tasks for today, list the high-priority ones, and move the overdue ones to the "Later" project
The Skill recognizes intent, fills in missing details, and assembles dida commands automatically — no manual parameters required.
Option 3: As an MCP Server
Exposes 44 tools as a standard MCP Server for Claude Code, Cursor, Windsurf, etc. See MCP Server integration.
Documentation
Doc | Contents |
All commands, parameters, conventions | |
Credentials, enabling V2, env vars, token lifecycle | |
Local / source / Docker deployment, AI tool config |
Development
uv sync # Install dependencies
uv run python -m pytest tests/ # Run tests
uv run ruff check src/ tests/ # Lint
uv run dida --help # Run the CLI locallyLicense
Acknowledgments
Available Tools
19 toolsdida365_batch_complete_tasksBatch Complete TasksBIdempotent
Mark multiple tasks in a project as completed.
Inputs: task_ids (required), project_id (required). Returns: result
dida365_batch_create_tasksBatch Create TasksA
Batch create multiple tasks in one request.
Each dict requires "title" and "projectId". Optional fields same as create_task. Returns {"id2etag": {...}, "id2error": {...}}.
Inputs: tasks (required). Returns: result
dida365_batch_update_tasksBatch Update TasksBIdempotent
Batch update multiple tasks in one request.
Each dict requires "id" and "projectId". Only provided fields are changed. Returns {"id2etag": {...}, "id2error": {...}}.
Inputs: tasks (required). Returns: result
dida365_complete_taskComplete TaskCIdempotent
Mark a task as completed.
Inputs: task_id (required), project_id (required). Returns: result
dida365_create_projectCreate ProjectC
Create a project. view_mode: list|kanban|timeline. kind: TASK|NOTE.
Inputs: name (required), kind, color, view_mode, +1 more. Returns: result
dida365_create_taskCreate TaskA
Create a task. Requires title and project_id.
Note: repeat_flag (RRULE) requires start_date to be set.
Args: column_id: Kanban column to place the task in (project must be kanban view). kind: TEXT (default), NOTE, or CHECKLIST. Set to CHECKLIST when passing items. sort_order: Display order; lower values appear first. items: Subtask list (for CHECKLIST kind). Each dict should contain at least "title" (required). Optional keys (camelCase): "status" (0=normal, 1=done), "sortOrder", "startDate", "isAllDay", "timeZone".
Inputs: project_id (required), desc, kind, tags, +11 more. Returns: result
dida365_delete_projectDelete ProjectADestructiveIdempotent
Permanently delete a project and all its tasks. This action cannot be undone.
Inputs: project_id (required). Returns: result
dida365_delete_taskDelete TaskBDestructiveIdempotent
Permanently delete a task. This action cannot be undone.
Inputs: task_id (required), project_id (required). Returns: result
dida365_filter_tasksFilter TasksCRead-onlyIdempotent
Filter tasks across projects. All parameters are optional and combinable.
Tags filter uses AND logic (tasks must match all specified tags).
Inputs: tags, status, end_date, priority, +2 more. Returns: result
dida365_get_completed_tasksList Completed TasksARead-onlyIdempotent
Get completed tasks, optionally filtered by project and completion time range.
Inputs: end_date, start_date, project_ids. Returns: result
dida365_get_projectGet ProjectCRead-onlyIdempotent
Get project details by ID.
Inputs: project_id (required). Returns: result
dida365_get_project_tasksList Project TasksBRead-onlyIdempotent
Get all uncompleted tasks in a project.
Inputs: project_id (required). Returns: result
dida365_get_taskGet TaskCRead-onlyIdempotent
Get a single task by ID.
Inputs: task_id (required), project_id (required). Returns: result
dida365_get_task_by_idGet Task By IDARead-onlyIdempotent
Get a task by ID without needing project_id.
Inputs: task_id (required). Returns: result
dida365_list_projectsList ProjectsARead-onlyIdempotent
List all projects. Call this first to discover project IDs for other operations.
Inputs: no named parameters. Returns: result
dida365_list_undone_tasksList Undone TasksCRead-onlyIdempotent
List undone tasks within a date range, optionally filtered by projects.
Inputs: end_date, start_date, project_ids. Returns: result
dida365_move_taskMove TaskCIdempotent
Move a task between projects.
Inputs: task_id (required), to_project_id (required), from_project_id (required). Returns: result
dida365_update_projectUpdate ProjectCIdempotent
Update a project. Only provided fields are changed.
Inputs: project_id (required), kind, name, color, +2 more. Returns: result
dida365_update_taskUpdate TaskBIdempotent
Update a task. Only provided fields are changed; omitted fields remain unchanged.
Args: column_id: Move the task to this kanban column (project must be kanban view). kind: TEXT, NOTE, or CHECKLIST. Set to CHECKLIST when passing items. sort_order: Display order; lower values appear first. items: Subtask list (for CHECKLIST kind). Each dict should contain at least "title" (required). Optional keys (camelCase): "status" (0=normal, 1=done), "sortOrder", "startDate", "isAllDay", "timeZone".
Inputs: task_id (required), project_id (required), desc, kind, +12 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Two tools (get_task and get_task_by_id) appear to do the same thing, and several retrieval tools (get_project_tasks, filter_tasks, list_undone_tasks, get_completed_tasks) overlap in purpose, though descriptions offer some differentiation. An agent could still misselect among task-listing tools.
All names use snake_case with a consistent dida365_ prefix and verb_noun structure. Minor deviations like get_task_by_id and mixed get/list verbs for retrieval prevent a perfect score.
19 tools is on the heavy side for a task manager, and a few are redundant (e.g., get_task_by_id), pushing it into the borderline range. Batch variants are justified but the set could be trimmed.
Core project and task lifecycle (create, read, update, delete, complete, move) is covered, plus batch operations and filtering. Minor gaps exist in tag management and batch deletion, but agents can work around them.
Maintenance
Related MCP Connectors
Official Todoist MCP server. Manage tasks and projects. Hosted, no API key needed.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for Google Tasks: review, plan and tidy your tasks by asking. Deletes always ask first.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that connects AI assistants to your TickTick tasks, enabling task management through natural language.81MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for TickTick/Dida365 task integration, enabling AI-driven task decomposition and management with automated OAuth authentication.10MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage TickTick tasks, projects, habits, and focus sessions through the MCP server.71 PyPI148MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for integrating TickTick task management with AI applications, enabling task and project operations via natural language.11 npmMIT