todo-tree MCP Server
Exposes your todo-tree task list as MCP tools for reading and managing tasks via MCP-compatible AI clients like Claude Desktop.
README
todo-tree MCP Server
Exposes your todo-tree task list as MCP tools so any MCP-compatible AI client (Claude Desktop, etc.) can read and manage your tasks. It supports both stdio transport (default) and SSE (HTTP) transport with dynamic client-side authentication.
Modes of Operation
1. SSE (HTTP) Mode with Web Portal (Recommended)
By defining the PORT environment variable, the server will boot as an HTTP server supporting Server-Sent Events (SSE). It hosts a web interface allowing non-technical users to easily log in and connect.
Setup
- Create a
.envfile based on.env.example:PORT=3001 TODO_TREE_API_URL=http://localhost:1337 - Start the server:
npm start - Open
http://localhost:3001in your browser. - Log in with your Todo Tree credentials to get your personalized connection URL and configuration block.
2. Deployed SSE Mode (No Local Repository Needed)
If the server has already been deployed to a cloud platform (such as Fly.io, Render, or a VPS), you do not need to clone the repository or run any code locally to connect your AI client.
Setup for Clients
- Open the public URL of the deployed server in your browser (for example,
https://your-todo-tree-mcp.com). - Log in with your Todo Tree credentials to access the connector dashboard.
- The dashboard will automatically generate the required configuration for your client.
- Copy the generated Claude Desktop configuration block.
- Open your local Claude Desktop configuration file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
- Paste the configuration block inside the
mcpServersobject:{ "mcpServers": { "todo-tree": { "url": "https://your-todo-tree-mcp.com/sse?token=YOUR_SECURE_TOKEN" } } } - Restart your Claude Desktop client.
3. Stdio Mode (Single User)
If no PORT is defined, the server runs in standard I/O mode. It uses a static token defined in the environment variables to authenticate all requests.
Setup for Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"todo-tree": {
"command": "node",
"args": ["C:\\Users\\davei\\Desktop\\todo-tree\\mcp-server\\dist\\index.js"],
"env": {
"TODO_TREE_API_URL": "http://localhost:1337",
"TODO_TREE_TOKEN": "your-jwt-token-here"
}
}
}
}
Environment Variables
| Variable | Required | Description |
|---|---|---|
PORT |
No | Port to run in SSE mode. If omitted, runs in stdio mode. |
TODO_TREE_API_URL |
No | Base URL of the Strapi backend (defaults to http://localhost:1337). |
TODO_TREE_TOKEN |
No | Static JWT/token (required only for Stdio mode). |
Development
Run without a build step using tsx:
PORT=3001 npm run dev
Test interactively with the MCP Inspector:
npx @modelcontextprotocol/inspector tsx src/index.ts
Tools
get_tree
Returns the full task tree as indented text. Each line shows the task ID in brackets, completion status, due date, and child progress. Use the IDs in subsequent tool calls.
[work] : Work
[finish-report] : Finish report
[review-pr] : Review PR - Due: Today
[buy-groceries] : Buy groceries - Due: May 30
[call-dentist] : Call dentist
add_task
Creates a new task.
| Parameter | Type | Required | Description |
|---|---|---|---|
text |
string | Yes | Task name |
parent_id |
string | No | ID of the parent task; omit for root level |
due_date |
string | No | Due date in YYYY-MM-DD format |
delete_task
Permanently removes a task and all its children.
| Parameter | Type | Required | Description |
|---|---|---|---|
id |
string | Yes | Task ID |
complete_task
Marks a task done or undone. Completion propagates to all child tasks, same as clicking the checkbox in the UI.
| Parameter | Type | Required | Description |
|---|---|---|---|
id |
string | Yes | Task ID |
completed |
boolean | No | true (default) to complete, false to uncomplete |
set_due_date
Sets or clears the due date on a task.
| Parameter | Type | Required | Description |
|---|---|---|---|
id |
string | Yes | Task ID |
due_date |
string | Yes | Date in YYYY-MM-DD, or "" to clear |
move_task
Moves a task to a new position in the tree.
| Parameter | Type | Required | Description |
|---|---|---|---|
id |
string | Yes | Task to move |
target_id |
string | Yes | Reference task |
position |
before | after | inside |
Yes | before/after makes it a sibling; inside makes it a child |
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。