Skip to main content
Glama
Sign In
Todoist MCP Server

Todoist MCP Server

by bkotos
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Todoist MCP Server

A TypeScript-based Model Context Protocol (MCP) server that provides Todoist task management capabilities to AI assistants. This MCP server is built for use with Claude Desktop and operates over stdio.

Note: This MCP server is tailored to my specific workflow with Todoist and may not align with how others use the tool.

Getting Started

Prerequisites

  • Node.js 18+

  • Todoist account with API access

Install

git clone <repository-url>
cd todoist-mcp
npm ci

Configure

cp env.example .env
# Add your Todoist API token to .env

Connect to Claude Desktop

1. Configure Claude Desktop

Edit your Claude Desktop configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%/Claude/claude_desktop_config.json

2. Add MCP Server Configuration

{
  "mcpServers": {
    "todoist": {
      "command": "$PATH_TO_REPO/start-mcp.sh",
      "args": [],
      "env": {}
    }
  }
}

Replace $PATH_TO_REPO with the absolute path of where you cloned this repo.

3. Restart Claude Desktop

Restart Claude Desktop completely for the changes to take effect.

4. Verify Connection

Test the connection by asking Claude to list your Todoist projects or tasks.

Available Tools

33 tools
complete_becky_taskB

Complete a Brian shared task (assigned to Brian from Becky) by setting due date to today, adding a completion comment, and moving it to Becky inbox project

Inputs: task_id (required).

complete_taskC

Complete a task by its ID

Inputs: task_id (required).

create_project_labelA

Create a new project label in Todoist. The label name must start with "PROJECT: " (with a space after the colon). The label will be created with charcoal color.

Inputs: project_name (required).

create_taskC

Create a new Todoist task with title, description, project, labels, priority, and due date. Only title is required.

Inputs: title (required), description, project_id, labels, +2 more.

create_task_commentB

Create a new comment on a specific Todoist task. The comment will automatically include a signature indicating it was created using Claude.

Inputs: task_id (required), content (required).

get_areas_of_focusB

Get all tasks from the "Areas of focus" project in Todoist. Returns structured JSON data with task details including id, content, description, priority, due date, labels, and more.

Inputs: no named parameters.

get_becky_shared_projectsC

Get projects that belong to Becky and are shared for tasks in her ballpark to handle per Brian

Inputs: no named parameters.

get_brian_only_projectsB

Get projects that belong only to Brian and are NOT shared

Inputs: no named parameters.

get_brian_shared_projectsC

Get projects that belong to Brian and are shared for tasks in his ballpark to handle per Becky

Inputs: no named parameters.

get_chores_due_todayA

Get all chores due today or overdue from Todoist using the filter "(today | overdue) & ##Chores". Returns structured JSON data with chore details including id, content, due date, project_id, and labels.

Inputs: no named parameters.

get_context_labelsA

Get all context labels from Todoist. Context labels are labels that start with "context:" and are used to organize tasks by context (e.g., context:home, context:office, context:mobile).

Inputs: no named parameters.

get_inbox_projectsB

Get the three inbox projects: Inbox, Brian inbox - per Becky, and Becky inbox - per Brian

Inputs: no named parameters.

get_recent_mediaA

Get all media tasks created in the last 30 days from Todoist, excluding subtasks and watched items. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

get_shopping_listB

Get all tasks from the "Shopping list" project in Todoist. Returns structured JSON data with task details including id, content, description, priority, due date, labels, and more.

Inputs: no named parameters.

get_task_commentsA

Get all comments for a specific Todoist task. Returns structured JSON data with comment details including id, content, posted date, user ID, and any attachments.

Inputs: task_id (required).

get_tasks_due_this_weekA

Get all tasks due this week (next 7 days) from Todoist, excluding various project categories. Returns structured JSON data with task details including id, content, due date, project id, and labels.

Inputs: no named parameters.

get_tasks_due_tomorrowA

Get all tasks due tomorrow from Todoist, excluding various project categories like Tickler, Chores, and baby-related projects. Returns structured JSON data with task details including id, content, due date, project id, and labels.

Inputs: no named parameters.

get_tasks_with_labelA

Get all tasks with a specific label that are not part of the "Brian projects" or "Projects" projects. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: label (required).

get_tickler_tasksA

Get all tickler tasks that are due today or overdue from Todoist. Tickler tasks are tasks with labels #Tickler, #Ansonia Tickler, or #Brian tickler. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

get_waiting_tasksA

Get all waiting tasks from Todoist using the filter "#Waiting | #Brian waiting | #Ansonia Waiting". Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_becky_inbox_per_brian_tasksA

List all Becky inbox per Brian tasks from Todoist using the ##Becky inbox - per Brian filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_becky_time_sensitive_tasksA

List all Becky time sensitive tasks from Todoist using the ##Becky time sensitive \(per BK\) & !subtask filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_brian_inbox_per_becky_tasksA

List all Brian inbox per Becky tasks from Todoist using the ##Brian inbox - per Becky filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_brian_time_sensitive_tasksA

List all Brian time sensitive tasks from Todoist using the ##Brian time sensitive \(per BP\) & !subtask filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_gtd_projectsA

List all GTD projects from Todoist using the (#Projects | #Brian projects | #Ansonia Projects) & !subtask filter, excluding baby-related projects. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_next_actionsA

List all next actions from Todoist using the (##Next actions | ##Brian acknowledged) & !subtask filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

list_personal_inbox_tasksA

List all personal inbox tasks from Todoist using the ##Inbox filter. Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: no named parameters.

move_taskC

Move a task from one project to another

Inputs: task_id (required), project_id (required).

search_tasksA

Search for tasks in Todoist using the search filter. This is one of three search tools: basic search (single term), AND search (all terms must match), and OR search (any term can match). Supports three search syntax options: basic text search (meeting), wildcard search (report), and exact phrase search ("buy groceries"). Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: query (required).

search_tasks_using_andA

Search for tasks in Todoist using AND logic - all search terms must be present. Search query examples: meeting (basic text search), report (wildcard search), "buy groceries" (quoted, exact phrase search). Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: search_terms (required).

search_tasks_using_orA

Search for tasks in Todoist using OR logic - any search term can match. Search query examples: meeting (basic text search), report (wildcard search), "buy groceries" (quoted, exact phrase search). Returns structured JSON data with task details including id, content, description, completion status, labels, priority, due date, and comment count.

Inputs: search_terms (required).

uncomplete_taskC

Uncomplete (reopen) a task by its ID

Inputs: task_id (required).

update_taskB

Update a Todoist task with new title, description, labels, priority, or due string. All fields are optional - only provided fields will be updated.

Inputs: task_id (required), title, description, labels, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 33 tools

    Disambiguation2/5

    Multiple tools have overlapping purposes, causing confusion. For example, there are three separate search tools (search_tasks, search_tasks_using_and, search_tasks_using_or) that could be consolidated, and several 'list_' tools (e.g., list_brian_time_sensitive_tasks, list_becky_time_sensitive_tasks) are very similar in function but differ only by user or filter. This overlap makes it difficult for an agent to choose the right tool without deep context.

    Naming Consistency3/5

    The naming is mixed but somewhat readable. Most tools use snake_case and start with verbs like 'get_', 'list_', 'create_', 'update_', 'complete_', which is consistent. However, there are inconsistencies such as 'complete_becky_task' vs. 'complete_task' (one is specific, the other general) and 'search_tasks' vs. 'search_tasks_using_and' vs. 'search_tasks_using_or' (redundant naming). Overall, the pattern is discernible but not fully uniform.

    Tool Count2/5

    With 33 tools, the count is excessive for a Todoist server, indicating poor scoping. Many tools are highly specific (e.g., get_chores_due_today, get_tickler_tasks) and could be generalized into fewer, more flexible tools. This bloated set increases complexity and reduces usability, as agents must navigate numerous similar tools for basic operations.

    Completeness4/5

    The tool surface covers core Todoist operations well, including CRUD for tasks (create, update, complete, uncomplete), project and label management, and various querying functions. However, there are minor gaps, such as no direct tool for deleting tasks or managing project settings beyond labels, which might require workarounds but doesn't severely hinder functionality.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers