google-tasks-mcp
Enables AI assistants to manage Google Tasks, including listing, creating, updating, deleting, and completing tasks via the Google Tasks API.
README
Google Tasks MCP Server
A Model Context Protocol (MCP) server for Google Tasks. Lets AI assistants list, create, update, delete, and complete tasks via the Google Tasks API.
Why this exists
I prefer Google Tasks over Google Calendar for managing todos. The excellent google-calendar-mcp project only covers the Calendar API, so I built this quick-and-dirty companion to fill the gap. If you'd like to fold Tasks support into that project, PRs are welcome there.
Quick Start
1. Enable the Google Tasks API
- Go to the Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Tasks API (make sure the correct project is selected in the top bar)
- Create OAuth 2.0 credentials:
- Go to Credentials
- Click Create Credentials > OAuth client ID
- Choose Desktop app as the application type
- Download the JSON file (you'll reference its path below)
- Configure the OAuth consent screen:
- Add your email as a Test User
- Note: test-mode tokens expire after 7 days (see Limitations)
2. Install
Add to your MCP client config (Cursor, Claude Desktop, etc.):
{
"mcpServers": {
"google-tasks": {
"command": "npx",
"args": ["-y", "@scottie-will/google-tasks-mcp"],
"env": {
"GOOGLE_OAUTH_CREDENTIALS": "/path/to/your/gcp-oauth.keys.json"
}
}
}
}
3. Authenticate
Option A — CLI (recommended for first run):
GOOGLE_OAUTH_CREDENTIALS=/path/to/gcp-oauth.keys.json npx @scottie-will/google-tasks-mcp auth
Complete the OAuth flow in your browser, then restart your MCP client.
Option B — Via the agent:
Ask your AI assistant to "authenticate with Google Tasks". The authenticate tool will return a URL to visit in your browser. After completing sign-in, tell the agent to verify authentication.
Available Tools
| Tool | Description |
|---|---|
authenticate |
Start or verify Google OAuth authentication |
list-task-lists |
List all task lists for the authenticated user |
list-tasks |
List tasks with optional date filtering and completion status |
get-task |
Get a specific task by ID |
create-task |
Create a new task (supports subtasks via parent) |
update-task |
Update an existing task (partial updates supported) |
delete-task |
Permanently delete a task |
complete-task |
Mark a task as completed |
Environment Variables
| Variable | Required | Description |
|---|---|---|
GOOGLE_OAUTH_CREDENTIALS |
Yes | Path to your OAuth credentials JSON file |
GOOGLE_TASKS_MCP_TOKEN_PATH |
No | Custom path for token storage (default: ~/.config/google-tasks-mcp/tokens.json) |
Limitations
- Dates only, no times. The Google Tasks API stores due dates only — any time component in the
duefield is silently discarded. Workaround: prefix the task title with a 24-hour time (e.g. "0900 Team standup") for manual time-based ordering. - Position-based ordering only. Tasks are returned in position order (the drag-order from the Google Tasks UI). There is no server-side sort by due date — sort client-side after fetching.
- No pagination. Each list call returns at most 100 items. Large task lists may be truncated.
- Test-mode token expiry. While your GCP app is in test mode, OAuth tokens expire after 7 days. To avoid this, publish your app to production (no verification needed for personal use — Google will show an "unverified app" warning).
- Single account. Only one Google account is supported at a time.
For full API details, see the Google Tasks API reference.
Agent Setup Instructions
This server includes built-in instructions metadata (via the MCP protocol) that teaches agents how to use it effectively — covering the auth flow, date-only behavior, sorting quirks, @default task list conventions, and destructive-operation guardrails. Compatible MCP clients (Cursor, Claude Desktop, etc.) surface these instructions automatically.
If your client supports serverUseInstructions in the MCP config, you can also add custom hints. See incident.io's MCP for an example of thorough server instructions.
GCP API Access Required
This server requires:
- API: Google Tasks API (
tasks.googleapis.com) - OAuth scope:
https://www.googleapis.com/auth/tasks(full read/write access to tasks) - Credential type: OAuth 2.0 Client ID — Desktop app type
No API key or service account is needed. The OAuth flow runs locally and tokens are stored on your machine at ~/.config/google-tasks-mcp/tokens.json.
Credits
- Inspired by and modeled after google-calendar-mcp by @nspady. That project covers the Google Calendar API with multi-account support, recurring events, and much more. If you'd like to add Tasks support there, open a PR — it would be a natural fit.
- Built with the Model Context Protocol SDK.
License
MIT
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。