# Google Tasks for AI agents. Managed auth, ready-made tools.

> Create, update, complete and review to-dos in Google Tasks on behalf of each of your users.

- Page: https://www.agent200.com/connectors/google-tasks/
- Category: Files and knowledge
- Authentication: Managed OAuth
- Identifier in code: `google_tasks`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Google Tasks, through Agent200. In code: "google_tasks".
What it does: Create, update, complete and review to-dos in Google Tasks on behalf of each of your users.
Page: https://www.agent200.com/connectors/google-tasks/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Google Tasks's own page, through the authorization link Agent200 returns. Never ask a user for a Google Tasks password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: google_tasks_list_tasklists, google_tasks_list_tasks. Write tools: google_tasks_create_task, google_tasks_update_task, google_tasks_complete_task, google_tasks_delete_task. Name "google_tasks" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/google-tasks/framework/claude/
   https://www.agent200.com/connectors/google-tasks/framework/chatgpt/
   https://www.agent200.com/connectors/google-tasks/framework/claude-code/
   https://www.agent200.com/connectors/google-tasks/framework/muse/
   https://www.agent200.com/connectors/google-tasks/framework/grok-bot/
   https://www.agent200.com/connectors/google-tasks/framework/openai-dots/
   https://www.agent200.com/connectors/google-tasks/framework/claude-duet/
   https://www.agent200.com/connectors/google-tasks/framework/hermes-agent/
   https://www.agent200.com/connectors/google-tasks/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Google Tasks connector, your agent manages to-dos in each user's own Google Tasks. It can list their task lists and tasks, add new tasks with due dates, update them, mark them done or delete them, using only the tools your project allows.

Google Tasks is Google's to-do list, built into Gmail, Calendar and its own app.

## Google Tasks tools

- **List task lists** (`google_tasks_list_tasklists`, read): List the user's task lists.
- **List tasks** (`google_tasks_list_tasks`, read): List the tasks in a task list.
- **Create a task** (`google_tasks_create_task`, write): Add a task with an optional due date and notes.
- **Update a task** (`google_tasks_update_task`, write): Change a task's title, notes or due date.
- **Complete a task** (`google_tasks_complete_task`, write): Mark a task as completed.
- **Delete a task** (`google_tasks_delete_task`, write): Remove a task from a list.

## Limits you can set

**Turn single tools on or off.** Let the agent read and add tasks, and switch off `google_tasks_delete_task` so it can never remove one.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example reading tasks but not changing them. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Google Tasks

Each end user authorizes their own Google Tasks account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Google Tasks account, once.
const connection = await agent200
  .user("user_123")
  .connect("google_tasks");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Google Tasks tools

Name the user, the model and the tools. The model decides which Google Tasks tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Add a task to renew the domain by Friday",
    tools: ["google_tasks"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Google's own sign-in page. You never see or store their Google password.

**What access is requested.** The scopes the connection needs, such as viewing tasks or managing tasks, listed on Google's authorization screen. Users can remove the app later from their Google Account settings.

## Example requests

- "Add a task to renew the domain by Friday"
- "What is on my to-do list this week"
- "Mark the invoice task as done"

## Guides: Google Tasks with your AI framework

- [Google Tasks + Claude](https://www.agent200.com/connectors/google-tasks/framework/claude.md): Set up Google Tasks for Claude with Agent200, then check which tools are available to your agent.
- [Google Tasks + ChatGPT](https://www.agent200.com/connectors/google-tasks/framework/chatgpt.md): Set up Google Tasks for ChatGPT with Agent200, then check which tools are available to your agent.
- [Google Tasks + Claude Code](https://www.agent200.com/connectors/google-tasks/framework/claude-code.md): Set up Google Tasks for Claude Code with Agent200, then check which tools are available to your agent.
- [Google Tasks + Muse](https://www.agent200.com/connectors/google-tasks/framework/muse.md): Set up Google Tasks for Muse with Agent200, then check which tools are available to your agent.
- [Google Tasks + Grok Bot](https://www.agent200.com/connectors/google-tasks/framework/grok-bot.md): Set up Google Tasks for Grok Bot with Agent200, then check which tools are available to your agent.
- [Google Tasks + OpenAI Dots](https://www.agent200.com/connectors/google-tasks/framework/openai-dots.md): Set up Google Tasks for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Google Tasks + Claude Duet](https://www.agent200.com/connectors/google-tasks/framework/claude-duet.md): Set up Google Tasks for Claude Duet with Agent200, then check which tools are available to your agent.
- [Google Tasks + Hermes Agent](https://www.agent200.com/connectors/google-tasks/framework/hermes-agent.md): Set up Google Tasks for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Google Tasks + OpenClaw](https://www.agent200.com/connectors/google-tasks/framework/openclaw.md): Set up Google Tasks for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Google Tasks OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Google Tasks.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Google Tasks connection, never another user's. It cannot reach anything the user or Google Tasks has not authorized.

### Can I limit what my agent can do in Google Tasks?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [Google Drive](https://www.agent200.com/connectors/google-drive.md): Find, read and organize the files in each user's Drive.
- [OneDrive](https://www.agent200.com/connectors/onedrive.md): Search, read, upload and share OneDrive files, including Word, Excel and PowerPoint documents, on behalf of each of your users.
- [Dropbox](https://www.agent200.com/connectors/dropbox.md): Search, read, upload and organize Dropbox files, and create shared links, on behalf of each of your users.
- [Notion](https://www.agent200.com/connectors/notion.md): Search, read and write Notion pages and databases on behalf of each of your users.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
