Google Tasks MCP Server

Developer ToolsTypeScript

Manage Google Tasks directly from your AI assistant

Available Tools

search

Search for tasks in Google Tasks

query

list

List all tasks in Google Tasks

cursor

create

Create a new task in Google Tasks

taskListIdtitlenotesdue

update

Update an existing task in Google Tasks

taskListIdidurititlenotesstatusdue

delete

Delete a task in Google Tasks

taskListIdid

clear

Clear completed tasks from a Google Tasks task list

taskListId

Google Tasks MCP provides a seamless integration between AI assistants and Google's task management system. This server enables you to search, list, create, update, and delete tasks directly through your AI assistant without switching contexts. With this integration, you can efficiently organize your to-do lists, set due dates, add notes to tasks, and mark items as complete—all through natural language interactions with your AI. The server handles OAuth authentication with Google's services to ensure secure access to your personal task data.

Overview

Google Tasks MCP allows your AI assistant to interact with your Google Tasks, providing a seamless way to manage your to-do lists through natural language commands.

Prerequisites

Before setting up the Google Tasks MCP, you'll need:

A Google account with access to Google Tasks
A Google Cloud project with the Google Tasks API enabled
Node.js installed on your system

Setup Instructions

Step 1: Create a Google Cloud Project

Go to the Google Cloud Console and create a new project
Navigate to "APIs & Services" > "Library" and enable the Google Tasks API
Set up the OAuth consent screen:
- Go to "APIs & Services" > "OAuth consent screen"
- Select "Internal" for testing purposes (or "External" if you plan to distribute)
- Add the scope https://www.googleapis.com/auth/tasks
- Complete the required information

Step 2: Create OAuth Credentials

Go to "APIs & Services" > "Credentials"
Click "Create Credentials" and select "OAuth client ID"
Choose "Desktop App" as the application type
Download the JSON file containing your OAuth keys
Rename the file to gcp-oauth.keys.json

Step 3: Install the MCP Server

You can install the Google Tasks MCP server using Smithery (recommended) or manually.

Option A: Install via Smithery

npx -y @smithery/cli install @zcaceres/gtasks --client claude

Option B: Manual Installation

Clone the repository:

git clone https://github.com/zcaceres/gtasks-mcp.git
cd gtasks-mcp

Install dependencies:
```
npm install
```
Build the server:
```
npm run build
```
Place your gcp-oauth.keys.json file in the root directory of the project

Step 4: Authenticate with Google

Run the authentication process:
```
npm run start auth
```
This will open a browser window where you'll need to sign in to your Google account and grant the necessary permissions
After successful authentication, credentials will be saved as .gdrive-server-credentials.json in the project root

Step 5: Configure Your AI Assistant

Add the server configuration to your AI assistant's configuration file:

For Claude Desktop:

Open the Claude Desktop app
Go to Settings > Advanced > Edit Configuration
Add the Google Tasks MCP server configuration to the JSON file

For other clients, add the appropriate configuration to connect to the Google Tasks MCP server.

Usage Tips

When creating tasks, you can specify a title, notes, and due date
Due dates should be in ISO format (YYYY-MM-DD)
You can search for tasks using keywords
To update a task, you'll need its ID and URI, which you can get from listing or searching for tasks
Use the "clear" function to remove all completed tasks from a task list

Troubleshooting

If authentication fails, delete the .gdrive-server-credentials.json file and try the authentication process again
Ensure your Google Cloud project has the Google Tasks API enabled
Check that your OAuth credentials are correctly configured with the necessary scopes
If you encounter permission issues, verify that you've granted the appropriate permissions during the OAuth flow