Google Tasks MCP Server

Google Tasks MCP Server

Enables LLMs like Claude to manage Google Tasks by listing, creating, updating, completing, and deleting tasks and task lists, including setting due dates and notes.

Category
访问服务器

README

Google Tasks MCP Server

A Model Context Protocol (MCP) server that provides access to your Google Tasks. This server enables LLMs (like Claude) to list, create, update, complete, and delete your Google Tasks.

Features

  • List Task Lists: View all your task lists.
  • Manage Tasks: Create, update, delete, and complete tasks.
  • Task Details: Set due dates, notes, and move tasks (subtasks).
  • FastMCP: Built using the fastmcp library for easy integration.

Setup

Prerequisites

  • Python 3.10 or higher
  • A Google Cloud Platform (GCP) Project
  • uv (recommended) or pip

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/gtasks-mcp.git
    cd gtasks-mcp
    
  2. Create a virtual environment and install dependencies:

    # Using uv (faster)
    uv venv
    source .venv/bin/activate
    uv pip install -r requirements.txt
    
    # OR using pip
    python3 -m venv venv
    source venv/bin/activate
    pip install -r requirements.txt
    

Google Cloud Setup

To use this server, you need to set up a Google Cloud project and enable the Tasks API.

  1. Create a Project: Go to the Google Cloud Console and create a new project.
  2. Enable API:
    • Go to APIs & Services > Library.
    • Search for "Google Tasks API" and click Enable.
  3. Configure Consent Screen:
    • Go to APIs & Services > OAuth consent screen.
    • Select External (unless you are a Google Workspace user and want Internal).
    • Fill in the required App Information (App name: "GTasks MCP", User support email, Developer contact email).
    • Click Save and Continue.
    • Scopes: Click Add or Remove Scopes. Filter for tasks. Select https://www.googleapis.com/auth/tasks (Access to your tasks).
    • Click Update and then Save and Continue.
    • Test Users: Add your own email address as a test user. This is critical while the app is in "Testing" mode.
  4. Create Credentials:
    • Go to APIs & Services > Credentials.
    • Click Create Credentials > OAuth client ID.
    • Application type: Desktop app.
    • Name: "GTasks MCP User".
    • Click Create.
  5. Download Client Secret:
    • Download the JSON file for your new OAuth client.
    • Rename the file to client_secret.json.
    • Move it to the root directory of this project.

Usage with Claude for Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "google-tasks": {
      "command": "/absolute/path/to/your/venv/bin/python",
      "args": [
        "/absolute/path/to/gtasks-mcp/server.py"
      ]
    }
  }
}

Note: Replace /absolute/path/to/ with the actual full paths on your machine.

Authentication

When you first run the server (or when Claude tries to use it), it will open a browser window asking you to log in with your Google account.

  1. Select the account you added as a Test User.
  2. You will likely see a "Google hasn't verified this app" warning. This is expected for personal testing apps.
  3. Click Advanced > Go to GTasks MCP (unsafe).
  4. Click Continue to grant access.
  5. The browser will show "The authentication flow has completed". You can close it.

A token.json file will be created to store your credentials for future use.

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选