Google Tasks MCP server
Turn work an agent discovers into tracked to-dos. This MCP server gives programmatic access to a user's task lists and the tasks inside them—creating tasks from meeting notes or tickets, nesting them as subtasks, reordering and moving them between lists, and reporting on what is overdue or recently finished.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers.
- API credentials for the application you're connecting (see the Authentication section on this page for what to collect).
Create an MCP server
Find the app in the catalog
- Sign in to AI Gateway and select App Catalog from the left navigation.
- Search for the application you want to connect, then select it from the catalog.
- Select Create MCP Server to start the wizard.
App Configuration
Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.
MCP Server Setup
- Enter a Name for your server — something descriptive that identifies both the application and its purpose.
- Enter a Description so your team knows what the server is for.
- Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
- Select Next.
Authentication
Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.
Review
Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
Authentication
Google Tasks API uses OAuth 2.0 for secure access. Set up your project in Google Cloud Console, enable the Google Tasks API, and create OAuth credentials. In Google Cloud Console, go to APIs & Services > Credentials and create a Web application OAuth 2.0 credential.
| Value | Setting |
|---|---|
| Redirect URI | https://auth.aigateway.cequence.ai/v1/outbound/oauth/callback |
| Auth endpoint | https://accounts.google.com/o/oauth2/v2/auth |
| Token endpoint | https://oauth2.googleapis.com/token |
| Scopes | https://www.googleapis.com/auth/tasks, https://www.googleapis.com/auth/tasks.readonly |
Google Tasks has only these two scopes—one read-only, one full access. There is no separate scope for creating tasks without also allowing deletion, so if you need an agent that can add but never remove, control that by choosing which tools to expose rather than by narrowing the scope.
Available tools
These tools cover the task lists a user owns and the tasks within them.
| Tool | Description |
|---|---|
| List task lists | Retrieve all of the user's task lists |
| Get task list | Retrieve a single task list by ID |
| Create task list | Add a new task list |
| Update task list | Replace a task list's properties |
| Patch task list | Change individual task list fields, such as the title |
| Delete task list | Remove a task list and everything in it |
| List tasks | Retrieve tasks in a list, with filters for due date, completion date, and last change |
| Get task | Retrieve a single task by ID |
| Create task | Add a task, optionally as a subtask of an existing one |
| Update task | Replace a task's fields, including marking it complete |
| Patch task | Change individual task fields, such as the due date |
| Delete task | Remove a task from a list |
| Move task | Reposition a task, change its parent, or move it to another list |
| Clear completed tasks | Hide all completed tasks in a list |
Tips
Use the tasks.readonly scope for agents that only summarize or report—a daily standup agent reading what is due does not need permission to change anything.
Create subtasks by passing the parent task's ID when you create the task, not by setting a parent field on the task itself. The parent is a parameter of the create operation, and a task created without it lands at the top level of the list.
Treat due dates as dates, not deadlines. Google Tasks stores only the date portion and discards the time, so an agent that sets a due time will find it silently dropped. If your workflow depends on a specific time, keep it in the task notes.
Remember that clearing completed tasks hides them rather than deleting them. They stop appearing in a normal listing but are still there—an agent that needs to report on finished work should ask for hidden and completed tasks explicitly, or it will report nothing.
Leave the delete tools out of the server if the agent's job is to add and organize work. Deleting a task list removes every task in it, and deleting a task that was assigned from Google Docs or Chat also removes the original in that surface.
Keep the limits in mind for bulk work: a user can have up to 2,000 task lists, 20,000 non-hidden tasks per list, 100,000 tasks in total, and 2,000 subtasks under a single task.
Cequence AI Gateway