todoist-mcp
Enables Claude Desktop and other MCP clients to manage Todoist tasks, projects, and labels through natural language.
README
<p align="center"> <img src="docs/logo.svg" width="120" alt="Todoist MCP logo"> </p>
Todoist MCP Server
A specialized Model Context Protocol (MCP) server for Todoist task management. This Docker-based server enables Claude Desktop and other MCP clients to interact with Todoist for creating, updating, and querying tasks.
Features
- Task Management: Create, update, complete, and delete tasks
- Smart Queries: Get tasks by project, label, priority, or filter
- Project & Label Management: Organize your tasks efficiently
- Redis Caching: Optional caching for improved performance
- Docker Support: Easy deployment with Docker and Docker Compose
Prerequisites
- Docker and Docker Compose (for containerized deployment)
- Todoist Account: Sign up for Todoist
- Todoist API Token: Get your token from Todoist Integration Settings
- Claude Desktop (optional): For MCP client integration
Quick Start
1. Clone and Configure
cd todoist-mcp
cp .env.example .env.local
Edit .env.local and add your Todoist API token:
TODOIST_API_TOKEN=your-todoist-api-token-here
DEBUG=false
# Optional Redis caching
REDIS_HOST=
REDIS_PORT=6379
REDIS_PASSWORD=
REDIS_USE_SSL=false
2. Run with Docker Compose
docker-compose up --build
The server will start in stdio mode, ready to accept MCP connections.
3. Connect to Claude Desktop
Add this configuration to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"todoist": {
"command": "docker",
"args": ["compose", "-f", "/path/to/todoist-mcp/docker-compose.yml", "run", "--rm", "todoist-mcp"]
}
}
}
Restart Claude Desktop to activate the server.
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
TODOIST_API_TOKEN |
Yes | - | Your Todoist API token |
DEBUG |
No | false |
Enable debug logging |
REDIS_HOST |
No | - | Redis server hostname (for caching) |
REDIS_PORT |
No | 6379 |
Redis server port |
REDIS_PASSWORD |
No | - | Redis password |
REDIS_USE_SSL |
No | false |
Use SSL for Redis connection |
Available MCP Tools
The Todoist MCP server provides the following tools:
Task Operations
create_task- Create a new taskupdate_task- Update an existing taskcomplete_task- Mark a task as completedelete_task- Delete a taskuncomplete_task- Reopen a completed task
Task Queries
get_tasks_today- Get all tasks due todayget_overdue_tasks- Get all overdue tasksget_tasks_by_project- Get tasks from a specific projectget_tasks_by_label- Get tasks with a specific labelget_tasks_by_priority- Get tasks by priority levelget_tasks_by_filter- Query tasks using Todoist filter syntax
Project Management
get_projects- List all projectscreate_project- Create a new projectupdate_project- Update a projectdelete_project- Delete a project
Label Management
get_labels- List all labelscreate_label- Create a new labelupdate_label- Update a labeldelete_label- Delete a label
Server Management
get_server_status- Check server healthget_server_config- View server configurationget_cache_stats- View cache performance metricsclear_cache- Clear cached dataget_cache_info- View Redis server information
Local Development
Without Docker
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Set environment variables:
export TODOIST_API_TOKEN=your-api-token
- Run the server:
python server.py
With Docker
Build and run:
docker build -t todoist-mcp .
docker run -e TODOIST_API_TOKEN=your-token todoist-mcp
Testing
Test Server Status
You can test the server by connecting via Claude Desktop and asking:
"What's the status of my Todoist server?"
Test Task Operations
"Create a task called 'Test task' in my Inbox" "Show me all tasks due today" "Mark task ID 12345 as complete"
Troubleshooting
"Todoist API token not configured"
Solution: Ensure TODOIST_API_TOKEN is set in your .env.local file or environment variables.
Connection Issues
Solution:
- Verify your API token is correct
- Check your internet connection
- Ensure Docker container has network access
Cache Not Working
Solution:
- Verify Redis connection settings
- Ensure Redis server is running
- Check Redis credentials and SSL settings
Architecture
The Todoist MCP server follows this architecture:
Claude Desktop
↓ (stdio)
Docker Container
↓
MCP Server (FastMCP)
↓
Todoist Service
↓
Todoist API
Optional Redis caching layer improves performance by reducing API calls.
Security Notes
- Never commit your
.env.localfile or API tokens to version control - Use environment-specific
.envfiles - Consider using Docker secrets for production deployments
- API tokens are never exposed through MCP tool responses
License
This project is provided as-is for personal use.
Support
For Todoist API documentation, visit: https://developer.todoist.com/
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.