TickTick MCP Server
Remote MCP server for managing TickTick tasks and projects, offering 22 tools for CRUD, search, and GTD workflows via any MCP client.
README
TickTick MCP Server
A remote Model Context Protocol (MCP) server for TickTick task management, hosted on Cloudflare Workers.
Provides 22 MCP tools for managing TickTick projects and tasks via any MCP client (Claude Desktop, etc.).
Features
- Project Management: Create, read, delete projects
- Task CRUD: Create, read, update, complete, delete tasks
- Search & Filter: Search tasks, filter by priority, date ranges
- GTD Support: Engaged tasks, next tasks, batch creation, subtasks
- Authentication: GitHub OAuth for MCP clients, TickTick API token for backend
Setup
1. Prerequisites
2. Clone and Install
git clone https://github.com/k-wakamatsu-tms/ticktick-mcp-server.git
cd ticktick-mcp-server
npm install
3. Configure Secrets
wrangler secret put GITHUB_CLIENT_ID
wrangler secret put GITHUB_CLIENT_SECRET
wrangler secret put GITHUB_ALLOWED_LOGINS
wrangler secret put COOKIE_ENCRYPTION_KEY
wrangler secret put TICKTICK_ACCESS_TOKEN
wrangler secret put TICKTICK_CLIENT_ID
wrangler secret put TICKTICK_CLIENT_SECRET
For local development, copy .dev.vars.example to .dev.vars and fill in the values.
4. Create KV Namespace
wrangler kv namespace create OAUTH_KV
Update the id in wrangler.jsonc with the returned namespace ID.
5. Deploy
npm run deploy
6. Connect from Claude Desktop
Add to your Claude Desktop MCP config:
{
"mcpServers": {
"ticktick": {
"command": "npx",
"args": [
"mcp-remote",
"https://ticktick-mcp-server.<your-subdomain>.workers.dev/mcp"
]
}
}
}
Local Development
cp .dev.vars.example .dev.vars
# Edit .dev.vars with your credentials
npm run dev
Available Tools (22)
Projects (4)
| Tool | Description |
|---|---|
get_projects |
Get all projects |
get_project |
Get a specific project |
create_project |
Create a new project |
delete_project |
Delete a project |
Task CRUD (6)
| Tool | Description |
|---|---|
get_project_tasks |
Get all tasks in a project |
get_task |
Get a specific task |
create_task |
Create a new task |
update_task |
Update an existing task |
complete_task |
Mark a task as complete |
delete_task |
Delete a task |
Search & Filter (8)
| Tool | Description |
|---|---|
get_all_tasks |
Get all tasks from all projects |
search_tasks |
Search tasks by keyword |
get_tasks_by_priority |
Filter by priority level |
get_tasks_due_today |
Tasks due today |
get_tasks_due_tomorrow |
Tasks due tomorrow |
get_tasks_due_in_days |
Tasks due in N days |
get_tasks_due_this_week |
Tasks due this week |
get_overdue_tasks |
Overdue tasks |
GTD & Batch (4)
| Tool | Description |
|---|---|
get_engaged_tasks |
High priority / due today / overdue |
get_next_tasks |
Medium priority / due tomorrow |
batch_create_tasks |
Create multiple tasks at once |
create_subtask |
Create a subtask under a parent |
Environment Variables
| Variable | Purpose |
|---|---|
GITHUB_CLIENT_ID |
GitHub OAuth App client ID |
GITHUB_CLIENT_SECRET |
GitHub OAuth App client secret |
GITHUB_ALLOWED_LOGINS |
Comma-separated allowed GitHub usernames (unset denies all access) |
COOKIE_ENCRYPTION_KEY |
Random key for cookie signing |
TICKTICK_ACCESS_TOKEN |
TickTick API access token |
TICKTICK_CLIENT_ID |
TickTick app client ID (for future refresh) |
TICKTICK_CLIENT_SECRET |
TickTick app client secret (for future refresh) |
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。