Google Tasks MCP Server

@ktmage

代码仓库

基本信息

分类

其他

许可证

MIT license

传输方式

stdio

作者

ktmage

关于 Google Tasks MCP Server

AI assistants and Google Tasks integration through Model Context Protocol.

#todo #mcp #mcp-server #modelcontextprotocol

Google Tasks MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-google-tasks-ktmage": {
      "command": "node",
      "args": [
        "build/index.js"
      ]
    }
  }
}

Google Tasks MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Google Tasks MCP Server?

An implementation for interacting with Google Tasks API through the Model Context Protocol (MCP). It enables MCP-compatible clients—such as Cursor—to use Google Tasks task management features directly from an AI assistant.

How to use Google Tasks MCP Server?

Clone the repository, install dependencies with npm install, enable the Google Tasks API in Google Cloud Console, and place a downloaded OAuth 2.0 desktop app credential file as credentials.json in the project root. Build with npm run build and run with node build/index.js; on first launch, a browser window prompts Google account authentication and generates a token.json for subsequent runs. For Cursor, add the server to ~/.cursor/mcp.json with "command": "node" and the full path to build/index.js.

Key features of Google Tasks MCP Server

Fetch all task list collections
List tasks within a specific task list
Create new tasks with optional notes and due date
Mark tasks as completed
Delete tasks

Use cases of Google Tasks MCP Server

Managing Google Tasks from an AI assistant in a Cursor IDE session
Automating task creation and completion based on AI-generated workflows
Querying task lists and individual tasks without leaving the development environment

常见问题

What dependencies and runtime are required?

Node.js 16 or higher and npm are required, along with a Google Cloud Project account with the Google Tasks API enabled.

How does authentication work?

OAuth 2.0 is used. A downloaded credentials JSON file (renamed to `credentials.json`) must be placed in the project root. On first run, a browser window asks for Google account authentication, which creates a `token.json` file used automatically thereafter.

Where are credentials and tokens stored?

The OAuth client file is stored as `credentials.json` in the project root. The authentication token is stored locally as `token.json` in the same directory.

What transports and authentication methods are supported?

The README specifies standard MCP stdio transport (via the `mcp.json` configuration) and OAuth 2.0 for Google Tasks API access. No other transports are mentioned.

What should I do if I get an "invalid_grant" error?

Delete the `token.json` file and re-authenticate. Also verify that the Google Tasks API is enabled for the project in the Google Cloud Console.

其他分类下的更多 MCP 服务器

Next Generation Movers: free moving quotes (remote MCP)

Next Generation Movers

Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K