Todoist MCP Server
A Model Context Protocol (MCP) server for Todoist, enabling advanced task and project management via Claude Desktop and other MCP-compatible clients.
Requirements
- Node.js (v18 or higher recommended)
- npm or yarn
- A Todoist account
- A Todoist API token (see https://todoist.com/prefs/integrations)
Features
- List, create, update, complete, reopen, and delete tasks
- List, create, update, archive, unarchive, and delete projects
- List, create, update, and delete sections
- List, create, update, and delete labels
- List, create, update, and delete comments
- Manage shared labels
- Fetch project collaborators
All Features
- Tasks: List, get, create, update, complete, reopen, delete
- Projects: List, get, create, update, archive, unarchive, delete
- Sections: List (by project), get, create, update, delete
- Labels: List, get, create, update, delete, manage shared labels
- Comments: List (by task/project), get, create, update, delete
- Collaborators: List project collaborators
Installation
For Claude Desktop (JSON)
If published as an npm package, you can use it directly with npx in your Claude Desktop configuration:
{
"mcpServers": {
"todoist": {
"command": "npx",
"args": [
"todoist-mcp"
],
"env": {
"TODOIST_API_TOKEN": "your_todoist_token"
}
}
}
}
- Set the
TODOIST_API_TOKENas shown.
Manual Installation
- Clone the repository:
git clone https://github.com/yourusername/todoist-mcp.git cd todoist-mcp - Install dependencies:
npm install # or yarn install - Build the project:
npm run build # or yarn build - Set your Todoist API token as an environment variable (see above).
- Run the built server:
node dist/server.js - Configure Claude Desktop to use your local build by adding this to your config file:
{ "mcpServers": { "todoist": { "command": "node", "args": [ "/path/to/todoist-mcp/dist/server.js" ], "env": { "TODOIST_API_TOKEN": "your_todoist_token" } } } }
Usage Examples
- Get top priority tasks:
"Show me my top priority tasks."
- Create and classify labels:
"Create labels for my tasks and classify them by project or urgency."
- Organize tasks by section:
"Move all tasks with the label 'urgent' to the 'Today' section."
- Project management:
"Create a new project called 'Personal Growth' and add a section 'Reading List'."
- Collaborator overview:
"List all collaborators for the project 'Team Launch'."
- Comment management:
"Add a comment to the task 'Prepare slides' with the content 'Remember to include Q2 results.'"
License
This project is licensed under the MIT License. See LICENSE for details.
Recommend MCP Servers 💡
@anshumax/world_bank_mcp_server
An MCP server enabling interaction with the World Bank open data API for AI assistants to list and analyze indicators
mcp-hfspace
An MCP server for integrating Hugging Face Spaces, including Gradio, with easy configuration and support for Claude Desktop mode, enabling various AI tasks like image generation, vision, and speech-to-text.
vibe-check-mcp-server
The definitive Vibe Coder's sanity check MCP server: Prevent cascading errors in AI workflows by implementing strategic pattern interrupts. Uses tool call "Vibe Check" with LearnLM 2.0 Flash, fine-tuned for pedagogy and metacognition to enhance complex workflow strategy, and prevents tunnel vision errors.
archethic-uco-mcp
MCP server providing real-time UCO token prices (USD/EUR) from Archethic's OracleChain via GraphQL API.
doris-mcp-server
Doris MCP (Model Context Protocol) Server is a backend service built with Python and FastAPI. It implements the MCP, allowing clients to interact with it through defined "Tools". It's primarily designed to connect to Apache Doris databases, potentially leveraging Large Language Models (LLMs) for tasks like converting natural language queries to SQL (NL2SQL), executing queries, and performing metadata management and analysis.

aywengo/kafka-schema-reg-mcp
A comprehensive Message Control Protocol (MCP) server for Kafka Schema Registry.