
Todoist MCP Server
A Model Context Protocol server that enables advanced task and project management in Todoist via Claude Desktop and other MCP-compatible clients.
README
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_TOKEN
as 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.
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.