mcp-todoist
MCP Server to create and manage tasks, projects, labels and more in Todoist, using their unified v1 API
README
Todoist MCP Server
MCP server enabling programmatic Todoist task and project management through an optimized tool set using Todoist REST API v1. Integrates seamlessly with Claude Desktop and other MCP-compatible clients.
Table of Contents
- Features
- Prerequisites
- Installation
- Configuration
- Available Tools
- Rate Limiting
- Development
- Contributing
- License
Features
- 7 Core Tools: Comprehensive task and project management
- Tasks (CRUD + complete/uncomplete)
- Projects (CRUD + archive/unarchive)
- Sections (organize tasks within projects)
- Comments (with file attachment support)
- Filters (custom task queries)
- Reminders (relative, absolute, location-based)
- Labels (personal and shared label management)
- Natural Language Dates: "tomorrow", "every Monday", "next Friday at 3pm"
- Deadline Support: Set completion deadlines distinct from due dates
- Batch Operations: Execute up to 100 operations per request via Sync API
- Smart Rate Limiting: Token bucket algorithm with automatic retry
- Type Safety: Full TypeScript implementation with Zod validation
- Comprehensive Testing: Contract and integration test coverage
Prerequisites
- Node.js 18 or higher
- Todoist account (Sign up free)
- Todoist API token (Get yours here)
- MCP client such as:
- Claude Desktop
- Raycast MCP Extension
- Any MCP-compatible client
Installation
- Clone the repository:
git clone https://github.com/shayonpal/mcp-todoist.git
cd mcp-todoist
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
1. Set up environment variables
cp .env.example .env
Edit .env and add your Todoist API token:
TODOIST_API_TOKEN=your_todoist_api_token_here
2. Configure your MCP client
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"todoist": {
"command": "node",
"args": ["/absolute/path/to/mcp-todoist/dist/server.js"],
"env": {
"TODOIST_API_TOKEN": "your_api_token_here"
}
}
}
}
Note: Use absolute paths in the configuration.
Other MCP Clients
Refer to your MCP client's documentation for configuration instructions. The server uses STDIO transport and follows MCP protocol version 2024-11-05.
Available Tools
todoist_tasks
Complete task management with create, get, update, delete, list, complete, and uncomplete actions. Supports natural language dates, deadlines, priorities, labels, and recurring tasks.
Key parameters: action, task_id, content, due_date, due_string, deadline, priority, labels, project_id
todoist_projects
Project management with create, get, update, delete, list, archive, and unarchive actions. Organize work with hierarchical projects and custom views.
Key parameters: action, project_id, name, color, is_favorite, view_style
todoist_sections
Section management within projects for better task organization. Create, get, update, delete, list, and reorder sections.
Key parameters: action, section_id, project_id, name, order
todoist_comments
Add and manage comments on tasks and projects with file attachment support (up to 15,000 characters).
Key parameters: action, comment_id, task_id, project_id, content, attachment
todoist_filters
Create and manage custom filters for advanced task queries. List, create, update, delete, and query filters.
Key parameters: action, filter_id, name, query, color, is_favorite
todoist_reminders
Set reminders for tasks with three types: relative (X minutes before due), absolute (specific datetime), and location-based (geofenced).
Key parameters: action, reminder_id, item_id, type, minute_offset, due, loc_lat, loc_long
todoist_labels
Manage personal and shared labels with create, get, update, delete, list, rename, and remove actions. Includes caching for optimal performance.
Key parameters: action, label_id, name, color, is_favorite, order
Rate Limiting
The server implements intelligent rate limiting to respect Todoist API constraints:
- REST API: 300 requests/minute (token bucket: 300 capacity, 5 tokens/sec refill)
- Sync API: 50 requests/minute (token bucket: 50 capacity, ~0.83 tokens/sec refill)
- Automatic Retry: Exponential backoff on 429 responses
- Batch Operations: Use for bulk updates to minimize API calls
Development
# Run in development mode with hot reload
npm run dev
# Build TypeScript
npm run build
# Run all tests
npm test
# Run tests in watch mode
npm run test:watch
# Generate test coverage report
npm run test:coverage
# Lint code
npm run lint
# Auto-fix linting issues
npm run lint:fix
# Format code with Prettier
npm run format
# Type-check without emitting
npm run typecheck
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
License
GNU General Public License v3.0 - see LICENSE for details.
Copyright (C) 2025 Shayon Pal
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。