About Google Tasks MCP Server
Google Tasks MCP Server connects Google Tasks to Claude and other MCP clients. It supports searching, listing, creating, updating and deleting tasks, and is aimed at users who want to manage to-do items through an AI assistant.
Key features
- 01Search and list tasks
- 02Create, update and delete tasks
- 03Clear completed tasks from a task list
- 04OAuth authentication for Google Tasks access
- 05Task details exposed as resources
Use cases
- 01Querying and organizing Google Tasks from Claude
- 02Clearing completed items from a task list in bulk
- 03Creating tasks from conversation content
MCP support
As an MCP server, it provides search, list, create, update, delete and clear tools to clients and exposes tasks as gtasks resources.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Tasks MCP Server
This MCP server integrates with Google Tasks to allow listing, reading, searching, creating, updating, and deleting tasks.
Components
Tools
-
search
- Search for tasks in Google Tasks
- Input:
query(string): Search query - Returns matching tasks with details
-
list
- List all tasks in Google Tasks
- Optional input:
cursor(string): Cursor for pagination - Returns a list of all tasks
-
create
- Create a new task in Google Tasks
- Input:
taskListId(string, optional): Task list IDtitle(string, required): Task titlenotes(string, optional): Task notesdue(string, optional): Due date
- Returns confirmation of task creation
-
update
- Update an existing task in Google Tasks
- Input:
taskListId(string, optional): Task list IDid(string, required): Task IDuri(string, required): Task URItitle(string, optional): New task titlenotes(string, optional): New task notesstatus(string, optional): New task status ("needsAction" or "completed")due(string, optional): New due date
- Returns confirmation of task update
-
delete
- Delete a task in Google Tasks
- Input:
taskListId(string, required): Task list IDid(string, required): Task ID
- Returns confirmation of task deletion
-
clear
- Clear completed tasks from a Google Tasks task list
- Input:
taskListId(string, required): Task list ID - Returns confirmation of cleared tasks
Resources
The server provides access to Google Tasks resources:
- Tasks (
gtasks:///<task_id>)- Represents individual tasks in Google Tasks
- Supports reading task details including title, status, due date, notes, and other metadata
- Can be listed, read, created, updated, and deleted using the provided tools
Getting started
- Create a new Google Cloud project
- Enable the Google Tasks API
- Configure an OAuth consent screen ("internal" is fine for testing)
- Add scopes
https://www.googleapis.com/auth/tasks - Create an OAuth Client ID for application type "Desktop App"
- Download the JSON file of your client's OAuth keys
- Rename the key file to
gcp-oauth.keys.jsonand place into the root of this repo (i.e.gcp-oauth.keys.json)
Make sure to build the server with either npm run build or npm run watch.
Installing via Smithery
To install Google Tasks Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @zcaceres/gtasks --client claude
Authentication
To authenticate and save credentials:
- Run the server with the
authargument:npm run start auth - This will open an authentication flow in your system browser
- Complete the authentication process
- Credentials will be saved in the root of this repo (i.e.
.gdrive-server-credentials.json)
Usage with Desktop App
To integrate this server with the desktop app, add the following to your app's server configuration:
{
"mcpServers": {
"gtasks": {
"command": "/opt/homebrew/bin/node",
"args": [
"{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
]
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.