Todoist MCP Server
Enables interaction with Todoist through the MCP interface, providing full CRUD operations for tasks and projects including creating, updating, completing, and filtering tasks with natural language commands.
README
Todoist MCP Server (TypeScript)
A Model Context Protocol (MCP) server for interacting with the Todoist API. This server provides CRUD operations for both Tasks and Projects through a standardized MCP interface, built with TypeScript and the official MCP SDK.
Features
Project Operations
- ✅ Create new projects
- ✅ Get project details
- ✅ List all projects
- ✅ Update project properties
- ✅ Delete projects
Task Operations
- ✅ Create new tasks
- ✅ Get task details
- ✅ List tasks with filtering
- ✅ Update task properties
- ✅ Complete tasks
- ✅ Reopen completed tasks
- ✅ Delete tasks
Setup
Prerequisites
- Node.js 18+
- npm or yarn
- Todoist API token
Installation
-
Clone or download the server code
-
Install dependencies:
npm install -
Get your Todoist API token:
- Go to Todoist Integrations
- Copy your API token
-
Set the environment variable:
export TODOIST_API_TOKEN=your_token_here
Building and Running
# Build the TypeScript code
npm run build
# Run the server
npm start
# Or build and run in one command
npm run dev
# For development with auto-rebuild
npm run watch
Configuration for Claude Desktop
Add the following to your Claude Desktop configuration file:
For macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
For Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": ["-y", "@angdrew/todoist-mcp-server"],
"env": {
"TODOIST_API_TOKEN": "your_token_here"
}
}
}
}
Available Tools
Project Tools
create_project
Create a new project in Todoist
- name (required): Project name
- color (optional): Project color
- viewStyle (optional): View style ("list" or "board")
- parentId (optional): Parent project ID for sub-projects
- isFavorite (optional): Mark as favorite
get_project
Get project details by ID
- projectId (required): Project ID
list_projects
List all projects (no parameters)
update_project
Update project properties
- projectId (required): Project ID
- name (optional): New name
- color (optional): New color
- viewStyle (optional): New view style
- isFavorite (optional): Favorite status
delete_project
Delete a project
- projectId (required): Project ID
Task Tools
create_task
Create a new task
- content (required): Task content
- description (optional): Task description
- projectId (optional): Project ID
- dueString (optional): Due date in natural language
- dueDate (optional): Due date (YYYY-MM-DD)
- dueDatetime (optional): Due datetime (RFC3339)
- priority (optional): Priority 1-4 (4 is highest)
- labels (optional): Array of labels
get_task
Get task details by ID
- taskId (required): Task ID
list_tasks
List tasks with optional filters
- projectId (optional): Filter by project ID
- filter (optional): Filter expression (e.g., 'today', 'overdue')
- label (optional): Filter by label
update_task
Update task properties
- taskId (required): Task ID
- content (optional): New content
- description (optional): New description
- dueString (optional): New due date
- dueDate (optional): New due date (YYYY-MM-DD)
- dueDatetime (optional): New due datetime
- priority (optional): New priority
- labels (optional): New labels array
complete_task
Mark a task as completed
- taskId (required): Task ID
reopen_task
Reopen a completed task
- taskId (required): Task ID
delete_task
Delete a task
- taskId (required): Task ID
Usage Examples
Once configured with Claude Desktop, you can use natural language commands:
- "Create a new project called 'Website Redesign'"
- "List all my projects"
- "Add a task 'Review mockups' to the Website Redesign project"
- "Show me all tasks due today"
- "Mark task 12345 as completed"
- "Update the task content to 'Review and approve mockups'"
Error Handling
The server includes comprehensive error handling for:
- Invalid API tokens
- Missing required parameters
- API rate limits
- Network errors
- Invalid project/task IDs
Development
Building
npm run build
Watch Mode
npm run watch
Project Structure
src/
├── index.ts # Main server implementation
├── types.ts # TypeScript type definitions (optional)
build/ # Compiled JavaScript output
├── index.js
├── index.d.ts
package.json # Project dependencies and scripts
tsconfig.json # TypeScript configuration
Dependencies
- @modelcontextprotocol/sdk: Official MCP SDK for TypeScript
- @doist/todoist-api-typescript: Official Todoist API TypeScript client
- zod: Schema validation library
License
This project is provided as-is for educational and personal use.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.