Google Tasks MCP server

Google Tasks MCP

English | Русский

A1 Google Tasks MCP lets an AI app manage Google Tasks in plain language. Plan a project as a task list, break work into subtasks with due dates and notes, mark things done and keep everything in order.

It uses the Google Tasks API with your Google account. It separates reversible completion from permanent deletion and makes the limits of the Tasks API explicit instead of implying that every to-do feature is possible.

• 21 tools. List, create and update task lists and tasks, move tasks, manage completion, sweep finished work and reach the raw API when a dedicated tool is missing.
• Connects from the conversation. Say "connect Google Tasks": the server walks you through the OAuth client, catches Google's redirect on 127.0.0.1 with PKCE and keeps the tokens itself — no config files, no restart.
• Completion is reversible, deletion is not. completetask has an undo (reopentask); the delete tools are separate and marked destructive.
• Due dates are honest. The API stores only the calendar date — the server never pretends to schedule a time of day; times belong in the notes.
• Minimal Google scope. A single tasks scope, without Drive, Calendar or Gmail access.

Start with a read-only question:

Show me my task lists and everything due before Friday in my default list.

Connect the server · Explore use cases · Open technical documentation

See it work in a minute

You: What's still open in the "Website launch" list, and what's due this week?

Assistant: Shows the open tasks with their due dates, notes and subtasks. Nothing changes.

You: Add a task "Send the launch announcement" due Friday as a subtask of "Marketing".

Assistant: Shows the target list, the parent task and the proposed task, then asks for confirmation before creating it.

You: Confirm.

Assistant: Creates the subtask with a Friday due date. It does not complete or delete anything unless you ask separately.

Contents

• Quick start
• What you can ask it to do
• How a task changes
• What can change
• Getting access
• Configuration
• Data, limits and background work
• Technical documentation
• Support

Quick start

You need Node.js 20+ and a Google account. Credentials are not required at install time — the server connects from the conversation.

1. Add the server to your AI app.
2. Say "connect Google Tasks": the assistant walks you through creating the OAuth client and approving access without editing config files.
3. Ask the read-only question above.

Codex

In the app: open Settings → MCP servers, select Add server, choose STDIO, enter the command npx -y mcp-google-tasks@latest and environment variables GOOGLETASKSCLIENTID, GOOGLETASKSCLIENTSECRET, GOOGLETASKSREFRESHTOKEN, then select Save and Restart**.

From the command line:

codex mcp add google-tasks \
  -- npx -y mcp-google-tasks@latest

codex mcp list

Shortened. The full README is on GitHub.