google-tasks-mcp
MCP server for the Google Tasks API that enables AI agents to read, create, update, delete, and manage Google Tasks.
README
google-tasks-mcp
MCP server for the Google Tasks API. It allows any AI agent (Claude, Cursor, and others) to read, create, update, and delete tasks via Google Tasks.
Tools
| Tool | What it does |
|---|---|
list_task_lists |
Lists all task lists |
list_tasks |
Lists tasks from a list (filters: date, status) |
get_task |
Returns a single task by ID |
create_task |
Creates a task (title, notes, due, parent) |
update_task |
Updates any task field |
complete_task |
Marks a task as completed |
delete_task |
Permanently deletes a task |
move_task |
Moves/reorders a task |
Setup (one-time)
1. Google Cloud Console
- Go to console.cloud.google.com
- Create a project (or select an existing one)
- Open APIs & Services -> Library -> find "Tasks API" -> Enable
- Open APIs & Services -> Credentials
- Create Credentials -> OAuth client ID
- Application type: Desktop app
- Name:
google-tasks-mcp
- Download the JSON file -> rename it to
.credentials.json-> place it in the project root
2. Install dependencies
npm install
3. Authorize (one-time)
npm run auth
A browser window will open -> approve Google access -> tokens will be saved to .tokens.json.
After this, re-authorization is not required because tokens are refreshed automatically.
Connect to Claude Desktop
Open claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add:
{
"mcpServers": {
"google-tasks": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/google-tasks-mcp/src/index.js"]
}
}
}
Restart Claude Desktop -> new tools will appear in the interface.
Connect to Claude Code
claude mcp add google-tasks -- node /ABSOLUTE/PATH/TO/google-tasks-mcp/src/index.js
Connect to Cursor / Windsurf / other agents
Any agent that supports MCP (stdio transport):
{
"mcpServers": {
"google-tasks": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/google-tasks-mcp/src/index.js"]
}
}
}
Example prompts for your agent
"Show all my tasks for this week"
"Create a task 'Open PR' with deadline 2026-03-05"
"Mark task X as completed"
"Move task Y to the top of the list"
Project structure
google-tasks-mcp/
├── src/
│ ├── index.js — MCP server (tools + handlers)
│ ├── auth.js — OAuth2 one-time setup
│ └── tasks-api.js — Google Tasks API wrapper
├── .credentials.json — (gitignored) your OAuth credentials
├── .tokens.json — (gitignored) access + refresh tokens
├── .credentials.example.json
├── .gitignore
└── package.json
Security
.credentials.jsonand.tokens.jsonmust never be committed (already in.gitignore)- Tokens are refreshed automatically via the
googleapisOAuth2 client
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。