Todoist MCP Server
Enables AI assistants to manage Todoist tasks, projects, comments, and labels through natural language commands. Provides complete CRUD operations securely via the Todoist REST API v2.
README
Todoist MCP Server
A Model Context Protocol (MCP) server that provides complete CRUD operations for Todoist tasks, projects, comments, and labels.
Purpose
This MCP server provides a secure interface for AI assistants to manage your Todoist tasks, projects, and more through natural language commands. It wraps the Todoist REST API v2 in a secure, Docker-based MCP server.
Features
Task Management (CRUD)
create_task- Create new tasks with content, description, due dates, priority, and labelslist_tasks- List all tasks with optional filtering by project, label, or custom filterget_task- Get detailed information about a specific taskupdate_task- Update task content, description, due date, priority, or labelscomplete_task- Mark a task as completedreopen_task- Reopen a completed taskdelete_task- Permanently delete a task
Project Management (CRUD)
create_project- Create new projects with name, color, favorite status, and view stylelist_projects- List all projects in your accountget_project- Get detailed information about a specific projectupdate_project- Update project name, color, favorite status, or view styledelete_project- Permanently delete a project
Comment Operations
create_comment- Add comments to taskslist_comments- List all comments for a task or project
Label Operations
create_label- Create new labels with name and colorlist_labels- List all labels in your account
Prerequisites
- Docker Desktop with MCP Toolkit enabled
- Docker MCP CLI plugin (
docker mcpcommand) - Todoist account with API token
Getting Your Todoist API Token
- Go to https://app.todoist.com/app/settings/integrations/developer
- Scroll down to find "API token"
- Copy the 40-character hexadecimal token
- Keep this token secure - it provides full access to your Todoist account
Installation
See the step-by-step instructions provided with the files.
Usage Examples
In Claude Desktop, you can ask:
Tasks
- "Create a task 'Buy groceries' due tomorrow with priority 2"
- "List all my tasks"
- "Show me tasks in project 12345"
- "Complete task 98765"
- "Update task 12345 to have priority 4 and due date 'next Monday'"
- "Delete task 98765"
Projects
- "Create a new project called 'Work Projects' with color blue"
- "List all my projects"
- "Update project 12345 to be a favorite"
- "Delete project 67890"
Comments & Labels
- "Add a comment 'Need to review this' to task 12345"
- "List comments for task 12345"
- "Create a label 'urgent' with color red"
- "Show me all my labels"
Architecture
Claude Desktop → MCP Gateway → Todoist MCP Server → Todoist REST API v2
↓
Docker Desktop Secrets
(TODOIST_API_TOKEN)
Development
Local Testing
# Set environment variable for testing
export TODOIST_API_TOKEN="your-api-token"
# Run directly
python todoist_server.py
# Test MCP protocol
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | python todoist_server.py
Adding New Tools
- Add the function to
todoist_server.py - Decorate with
@mcp.tool() - Update the catalog entry with the new tool name
- Rebuild the Docker image
Troubleshooting
Tools Not Appearing
- Verify Docker image built successfully:
docker images | grep todoist-mcp-server - Check catalog and registry files
- Ensure Claude Desktop config includes custom catalog
- Restart Claude Desktop
Authentication Errors
- Verify API token with
docker mcp secret list - Ensure secret name is exactly
TODOIST_API_TOKEN - Test token at https://developer.todoist.com/rest/v2/
API Rate Limits
- Todoist allows 1000 requests per 15 minutes per user
- If you hit limits, wait 15 minutes before retrying
Security Considerations
- All credentials stored in Docker Desktop secrets
- Never hardcode API tokens
- Running as non-root user
- API tokens never logged
- All communication over HTTPS
API Reference
This server uses Todoist REST API v2:
- Documentation: https://developer.todoist.com/rest/v2/
- Base URL: https://api.todoist.com/rest/v2
License
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。