MCP Servers

todoist-mcp

An MCP server that provides AI assistants with full access to Todoist tasks, projects, labels, and filters. It enables comprehensive task management, project organization, and productivity tracking through a wide range of specialized tools.

README

todoist-mcp

An MCP (Model Context Protocol) server for Todoist that gives AI assistants full access to your tasks, projects, labels, filters, comments, and more.

Built on the official @doist/todoist-ai package.

Tools

Tasks

Tool	Description
`add-tasks`	Create one or more tasks
`find-tasks`	Search and filter tasks
`find-tasks-by-date`	Find tasks by due date or date range
`find-completed-tasks`	Find previously completed tasks
`update-tasks`	Update existing tasks
`complete-tasks`	Mark tasks as complete
`uncomplete-tasks`	Reopen completed tasks
`reschedule-tasks`	Change task due dates

Projects

Tool	Description
`add-projects`	Create new projects
`find-projects`	Search and list projects
`update-projects`	Update project properties
`project-management`	Archive or unarchive projects
`project-move`	Move projects between workspaces

Sections

Tool	Description
`add-sections`	Create sections within projects
`find-sections`	Search and list sections
`update-sections`	Update section properties

Comments

Tool	Description
`add-comments`	Add comments to tasks or projects
`find-comments`	Search and list comments
`update-comments`	Update existing comments
`view-attachment`	View file attachments on comments

Labels

Tool	Description
`add-labels`	Create new labels
`find-labels`	Search and list labels

Filters

Tool	Description
`add-filters`	Create saved filters
`find-filters`	Search and list filters
`update-filters`	Update existing filters

Collaboration

Tool	Description
`find-project-collaborators`	List collaborators on a project
`manage-assignments`	Assign or unassign tasks
`list-workspaces`	List available workspaces

General

Tool	Description
`get-overview`	Get a summary of your Todoist account
`search`	Full-text search across Todoist
`fetch`	Fetch a Todoist URL
`fetch-object`	Fetch a specific task, project, section, or comment by ID
`delete-object`	Delete a task, project, section, label, or other object
`reorder-objects`	Reorder tasks, projects, or sections
`find-activity`	View activity/audit log
`get-productivity-stats`	Get your productivity statistics
`user-info`	Get current user information

Environment Variables

Variable	Required	Description
`TODOIST_API_KEY`	Yes	Your Todoist API token (get it from Settings > Integrations > Developer)

Installation

npm ci

Usage

Stdio mode (for Claude Desktop, etc.)

TODOIST_API_KEY=your_api_key node dist/main.js

Or create a .env file with your API key:

TODOIST_API_KEY=your_api_key

Then run:

node dist/main.js

HTTP mode (standalone server)

TODOIST_API_KEY=your_api_key node dist/main-http.js

The server starts on port 3000 by default (set PORT to override). The MCP endpoint is at /mcp and a health check is at /health.

HTTP mode with mcp-proxy

mcp-proxy --port 8006 -- node dist/main.js

Claude Desktop configuration

Add to your Claude Desktop MCP config:

{
  "mcpServers": {
    "todoist": {
      "command": "node",
      "args": ["/path/to/todoist-mcp/dist/main.js"],
      "env": {
        "TODOIST_API_KEY": "your_api_key"
      }
    }
  }
}

License

MIT

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.

Official

Featured

TypeScript

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.

Official

Featured

Local

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

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

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

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

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

Official

Featured