todoist-api-mcp
MCP server for Todoist API integration, allowing management of tasks, projects, sections, labels, and comments through natural language.
README
📝 Todoist-API-MCP
MCP server for Todoist API integration. Provides full access to Todoist functionality through a simple and convenient MCP protocol.
Key Features
- 🔄 Transport flexibility: support for various transport types - stdio, SSE, and HTTP Stream for different use cases
- 👥 Multi-user mode: in SSE/HTTP Stream modes, each client uses their own Todoist API token
- 🔒 Security: ability to restrict server access using an MCP Access token
- 🚀 Complete API: support for all main Todoist entities (tasks, projects, sections, labels, comments)
Quick Start
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": ["todoist-api-mcp", "--mode", "stdio"],
"env": {
"TODOIST_API_TOKEN": "your_todoist_api_token"
}
}
}
}
Advanced usage
# stdio mode (for single user)
npx todoist-api-mcp --mode stdio --todoist-token YOUR_TODOIST_API_TOKEN
# SSE mode (for multi-user access)
# Clients send their Todoist tokens via Authorization: Bearer TOKEN header
npx todoist-api-mcp --mode sse
# HTTP Stream mode (for multi-user access)
# Clients send their Todoist tokens via Authorization: Bearer TOKEN header
npx todoist-api-mcp --mode httpStream
# With MCP Access token restriction
npx todoist-api-mcp --mode sse --mcp-access-token YOUR_MCP_ACCESS_TOKEN
# Setting the port for HTTP modes
npx todoist-api-mcp --mode sse --port 8080
Transport Modes
-
stdio: local mode for working through standard input/output streams. The Todoist API token is passed through the
--todoist-tokenparameter or theTODOIST_API_TOKENenvironment variable. -
sse (Server-Sent Events): HTTP mode with event support for multiple clients. Each client uses their own Todoist API token via the
Authorization: Bearer TOKENheader. Server access can be restricted through an MCP Access token (--mcp-access-token), which is verified in theX-Mcp-Tokenheader. -
httpStream: streaming HTTP mode for long-lived connections. Each client uses their own Todoist API token via the
Authorization: Bearer TOKENheader. Server access can be restricted through an MCP Access token (--mcp-access-token), which is verified in theX-Mcp-Tokenheader.
Available Tools
✅ Tasks
- Reading: retrieving task lists and detailed information
- Creating: adding new tasks with support for all Todoist parameters
- Updating: changing any parameters of existing tasks
- Closing/Opening: managing task completion status
- Deleting: completely removing tasks from Todoist
📁 Projects
- Reading: retrieving project lists and their contents
- Creating: adding new projects with parameter configuration
- Updating: changing parameters of existing projects
- Deleting: completely removing projects from Todoist
📋 Sections
- Reading: retrieving section lists and their contents
- Creating: adding new sections to projects
- Updating: changing parameters of existing sections
- Deleting: removing sections from projects
🏷️ Labels
- Reading: retrieving label lists
- Creating: adding new labels
- Updating: changing parameters of existing labels
- Deleting: removing labels from Todoist
💬 Comments
- Reading: retrieving comments for tasks and projects
- Creating: adding new comments
- Updating: changing comment content
- Deleting: removing comments
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。