mcp_google_tasks

mcp_google_tasks

0
cloud_platformsai_chatbot

The Google Tasks MCP Server is designed to connect AI assistants with the Google Tasks API using the Model Context Protocol. It allows for efficient task management including listing, creating, organizing, and completing tasks. It supports AI models capable of interacting with custom tools, enhancing productivity and task organization.

Google Tasks MCP Server

This project is a Model Context Protocol (MCP) server built in Python that allows Large Language Models (LLMs) like Claude.ai to interact with the Google Tasks API. The server provides a set of tools that enable AI assistants to manage your Google Tasks directly.

Authors

  • andiazo
  • cursor
  • gpt-4o and claude-3.7-sonnet

Features

  • List all your Google Task lists
  • Create new task lists
  • View tasks within a specific list
  • Add new tasks with titles, notes, and due dates
  • Mark tasks as completed
  • Move tasks between lists

Use Cases

  • Task Prioritization: Ask your AI assistant to analyze and prioritize your tasks based on due dates and importance
  • Task Organization: Have your AI assistant create and organize task lists for different projects
  • Task Management: Request your AI to add, update, or complete tasks during a conversation
  • Task Summarization: Get summaries of your upcoming tasks across different lists
  • Task Planning: Work with your AI to plan your day or week based on your existing tasks

Setup Instructions

Prerequisites

  • Python 3.8 or higher
  • Google Cloud Console account
  • Google Tasks API enabled

Installation

  1. Clone this repository:

    git clone https://github.com/andiazo/mcp_google_tasks.git
cd mcp_google_tasks

  2. Create and activate a virtual environment using uv:

    uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

  3. Install dependencies:

    uv add install -r requirements.txt

Google Cloud Console Setup

  1. Go to the Google Cloud Console
  2. Create a new project or select an existing one
  3. Enable the Google Tasks API for your project
  4. Create OAuth 2.0 credentials:
    • Go to "APIs & Services" > "Credentials"
    • Click "Create Credentials" > "OAuth client ID"
    • Select "Desktop app" as the application type
    • Download the credentials JSON file
  5. Rename the downloaded file to credentials.json and place it in the project root directory

Running the Server

  1. Start the MCP server:

    uv run google_tasks.py

  2. On first run, you'll be prompted to authorize the application:

    • A browser window will open
    • Log in with your Google account
    • Grant the requested permissions
    • The authorization will be saved to token.json for future use

  3. The server will now be running and ready to connect to your AI assistant

Connecting to AI Assistants

This MCP server can be used with any AI assistant that supports the Model Context Protocol, such as Claude.ai. Follow the specific instructions for your AI platform to connect to custom tools.

Claude: https://modelcontextprotocol.io/quickstart/server

Security Note

The credentials.json and token.json files contain sensitive authentication information. They are included in the .gitignore file to prevent accidental commits, but you should take additional precautions to keep them secure.