todoist-mcp-lite

todoist-mcp-lite

Minimal Todoist MCP server that provides direct passthrough to the Todoist REST API v2, supporting all HTTP methods via a single tool.

Category
Visit Server

README

@sjalq/todoist-mcp-lite

Minimal Todoist MCP server with direct API passthrough. Built with pure functional principles and minimal code.

Features

  • โœจ Single tool with direct Todoist REST API v2 passthrough
  • ๐Ÿš€ Supports all HTTP methods (GET, POST, PUT, PATCH, DELETE)
  • ๐Ÿ”’ CLI --token flag or environment variable authentication
  • ๐Ÿ“ฆ NPX-ready - no installation required
  • ๐Ÿงช Comprehensive test suite (property-based + integration + MCP protocol tests)
  • ๐ŸŽฏ Pure functional JavaScript - minimal dependencies
  • ๐Ÿ’ก Token-efficient tool descriptions

Getting Your Todoist API Token

  1. Log in to Todoist
  2. Go to Settings โ†’ Integrations โ†’ Developer
  3. Copy your API token from the "API token" section

Usage

Via NPX (recommended)

npx @sjalq/todoist-mcp-lite --token YOUR_TODOIST_TOKEN

Or with environment variable:

export TODOIST_API_TOKEN=YOUR_TODOIST_TOKEN
npx @sjalq/todoist-mcp-lite

In Claude Desktop config

Add to your ~/.claude.json:

{
  "mcpServers": {
    "todoist": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@sjalq/todoist-mcp-lite"],
      "env": {
        "TODOIST_API_TOKEN": "your_token_here"
      }
    }
  }
}

Or with --token flag:

{
  "mcpServers": {
    "todoist": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@sjalq/todoist-mcp-lite", "--token", "your_token_here"]
    }
  }
}

Tool

The server exposes a single tool: todoist_api

Parameters

  • endpoint (string, required): API endpoint (e.g., /tasks, /projects/123)
  • method (string, required): HTTP method (GET, POST, PUT, PATCH, DELETE)
  • body (object, optional): Request body for POST/PUT/PATCH requests

Response

Returns JSON with:

  • status: HTTP status code
  • ok: boolean indicating success
  • data: Response data from Todoist API (or error object)

Example

{
  "endpoint": "/tasks",
  "method": "POST",
  "body": {
    "content": "Buy milk",
    "due_string": "tomorrow"
  }
}

API Documentation

Full Todoist REST API v2 docs: https://developer.todoist.com/rest/v2

Development

Clone and Install

git clone https://github.com/sjalq/todoist-mcp-lite.git
cd todoist-mcp-lite
npm install

Running Tests

Property-based tests run without API token:

npm test

Integration and MCP protocol tests require a token:

export TODOIST_API_TOKEN=your_token
npm test

Test suite includes:

  • 4 property-based tests (pure function validation)
  • 6 integration tests (real API calls)
  • 4 MCP protocol tests (full server/client interaction)

Local Testing with MCP Inspector

npx @modelcontextprotocol/inspector node index.js --token YOUR_TOKEN

Then open http://localhost:6274 to interactively test the server.

Architecture

Pure functional design with three core functions:

  • getToken(args) - Extract token from CLI args or environment
  • callTodoist(token) - Curried API caller returning async function
  • createServer(apiCall) - MCP server factory with tool registration

Zero mocks, zero state, just functions.

License

ISC - see LICENSE file for details.

Contributing

Issues and PRs welcome at https://github.com/sjalq/todoist-mcp-lite

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured