Google Tasks MCP Server

Google Tasks MCP Server

Enables AI agents to securely authenticate with Google Tasks and perform full CRUD operations on task lists and tasks, including moving tasks and clearing completed tasks.

Category
访问服务器

README

Google Tasks MCP Server (vrob)

A robust, persistent Model Context Protocol (MCP) server for Google Tasks with seamless OAuth2 flow and reliable token refresh capabilities. This server allows AI agents (like Claude) to securely authenticate with Google Tasks and perform full CRUD operations on Task Lists and Tasks.

Features

  • 🔐 Persistent OAuth2 Authentication: Authenticate once, the token is saved securely and automatically refreshed in the background.
  • 🔄 Auto-Refresh Tokens: Avoids common "token expired" issues.
  • 📋 Full CRUD for Task Lists: Create, read, update, and delete task lists.
  • Full CRUD for Tasks: Create, read, update status (completed/needsAction), and delete specific tasks.
  • 📦 Move & Clear: Change task positions or clear all completed tasks.

Prerequisites

  • Node.js >= 20.0.0
  • Google Cloud Console account

Step-by-Step Guide

Step 1: Set Up Google Cloud Console

To use this MCP server, you need to create OAuth2 credentials from Google Cloud.

  1. Go to Google Cloud Console.
  2. Create a New Project (or select an existing one).
  3. In the navigation menu, go to APIs & Services > Library.
  4. Search for Google Tasks API, then click Enable.
  5. Go to APIs & Services > OAuth consent screen:
    • Select External (or Internal if you are using a Google Workspace).
    • Fill in the app name (e.g., "MCP Tasks"), user support email, and developer contact information.
    • In the Scopes section, click Add or Remove Scopes, then search for and add the https://www.googleapis.com/auth/tasks scope.
    • Add your own email in the Test users section (Required if the publishing status is set to "Testing").
  6. Go to APIs & Services > Credentials:
    • Click Create Credentials > OAuth client ID.
    • Application type: Select Web application.
    • Name: "MCP Server" (or anything you prefer).
    • Authorized redirect URIs: Add http://localhost:3000/oauth2callback. (You can change the port using .env if necessary).
    • Click Create.
  7. You will get a Client ID and a Client Secret. Save them!

Step 2: Configure Claude / Your MCP Client

Since the package is published on NPM, you can run it directly using npx without downloading the code manually.

Add the following configuration to your Claude Desktop settings file (claude_desktop_config.json):

{
  "mcpServers": {
    "google-tasks-vrob": {
      "command": "npx",
      "args": ["-y", "mcp-googletasks-vrob"],
      "env": {
        "GOOGLE_CLIENT_ID": "<YOUR_CLIENT_ID>",
        "GOOGLE_CLIENT_SECRET": "<YOUR_CLIENT_SECRET>",
        "OAUTH_PORT": "3000"
      }
    }
  }
}

Note: Replace <YOUR_CLIENT_ID> and <YOUR_CLIENT_SECRET> with the credentials you obtained in Step 1.

Step 3: Authentication & Usage

  1. Run your AI app/Claude Desktop. This MCP server will be loaded automatically.
  2. For the very first usage, ask the AI (Claude) to log in using a prompt like:

    "Please authenticate with Google Tasks"

  3. Claude will call the authenticate tool and provide you with a URL.
  4. Open the URL in your web browser, select your Google account, grant permission, and you will see an "✅ Authenticated!" message.
  5. That's it! You can now ask Claude to manage your tasks. For example:
    • "List all my task lists."
    • "Create a new task named 'Weekly Groceries' and put it in the 'Personal' list."
    • "Mark the 'Weekly Groceries' task as completed."

Alternative: Local Development Installation

If you want to modify the code or run it locally from the source:

git clone https://github.com/kokohbudi/mcp-googletasks-vrob.git
cd mcp-googletasks-vrob
npm install
npm run build

Then in your Claude config, point it to the local build:

"command": "node",
"args": ["/absolute/path/to/mcp-googletasks-vrob/build/index.js"],

List of Tools Available

This server exposes the following MCP tools:

Authentication Tools:

  • authenticate: Start the OAuth2 flow to log in.
  • auth-status: Check the current token status.
  • logout: Revoke the token and remove local credentials.

Task List Tools:

  • list-tasklists: List all task lists.
  • get-tasklist: Retrieve details of a specific task list.
  • create-tasklist: Create a new task list.
  • update-tasklist: Rename a task list.
  • delete-tasklist: Delete a task list.

Task Tools:

  • list-tasks: List tasks within a specific task list.
  • get-task: Retrieve details of a specific task.
  • create-task: Create a new task.
  • update-task: Change a task's notes, due date, title, or status.
  • delete-task: Delete a task.
  • complete-task: Instantly mark a task as completed.
  • move-task: Move a task's position within a list.
  • clear-completed-tasks: Delete all completed tasks from a list.

Local Credentials Storage

After a successful login, your OAuth2 credentials and Refresh Token are securely saved on your local machine:

  • macOS/Linux: ~/.config/mcp-googletasks-vrob/credentials.json
  • Windows: %USERPROFILE%\.config\mcp-googletasks-vrob\credentials.json

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